Min Zhang


2024

pdf bib
CMD: a framework for Context-aware Model self-Detoxification
Zecheng Tang | Keyan Zhou | Juntao Li | Yuyang Ding | Pinzheng Wang | Yan Bowen | Renjie Hua | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Text detoxification aims to minimize the risk of language models producing toxic content. Existing detoxification methods of directly constraining the model output or further training the model on the non-toxic corpus fail to achieve a decent balance between detoxification effectiveness and generation quality. This issue stems from the neglect of constrain imposed by the context since language models are designed to generate output that closely matches the context while detoxification methods endeavor to ensure the safety of the output even if it semantically deviates from the context. In view of this, we introduce a Context-aware Model self-Detoxification (CMD) framework that pays attention to both the context and the detoxification process, i.e., first detoxifying the context and then making the language model generate along the safe context. Specifically, CMD framework involves two phases: utilizing language models to synthesize data and applying these data for training. We also introduce a toxic contrastive loss that encourages the model generation away from the negative toxic samples. Experiments on various LLMs have verified the effectiveness of our MSD framework, which can yield the best performance compared to baselines.

pdf bib
Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment
Zhenyu Liu | Dongfang Li | Xinshuo Hu | Xinping Zhao | Yibin Chen | Baotian Hu | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Recent studies have explored the working mechanisms of In-Context Learning (ICL). However, they mainly focus on classification and simple generation tasks, limiting their broader application to more complex generation tasks in practice. To address this gap, we investigate the impact of demonstrations on token representations within the practical alignment tasks. We find that the transformer embeds the task function learned from demonstrations into the separator token representation, which plays an important role in the generation of prior response tokens. Once the prior response tokens are determined, the demonstrations become redundant. Motivated by this finding, we propose an efficient Progressive In-Context Alignment (PICA) method consisting of two stages. In the first few-shot stage, the model generates several prior response tokens via standard ICL while concurrently extracting the ICL vector that stores the task function from the separator token representation. In the following zero-shot stage, this ICL vector guides the model to generate responses without further demonstrations. Extensive experiments demonstrate that our PICA not only surpasses vanilla ICL but also achieves comparable performance to other alignment tuning methods. The proposed training-free method reduces the time cost (e.g., 5.45×) with improved alignment performance (e.g., 6.57+). Consequently, our work highlights the application of ICL for alignment and calls for a deeper understanding of ICL for complex generations. The code will be available at https://github.com/HITsz-TMG/PICA.

pdf bib
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
Xinping Zhao | Dongfang Li | Yan Zhong | Boren Hu | Yibin Chen | Baotian Hu | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanilla model as an evidence extractor with desired properties through self-aligned learning. Extensive experiments show that our method largely improves the final RAG performance, enhances the faithfulness, helpfulness, and conciseness of the extracted evidence, and reduces the evidence length by 9.25 times. The code will be available at https://github.com/HITsz-TMG/SEER.

pdf bib
A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models
Jiayin Wang | Fengran Mo | Weizhi Ma | Peijie Sun | Min Zhang | Jian-Yun Nie
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Large language models (LLMs) are essential tools that users employ across various scenarios, so evaluating their performance and guiding users in selecting the suitable service is important. Although many benchmarks exist, they mainly focus on specific predefined model abilities, such as world knowledge, reasoning, etc. Based on these ability scores, it is hard for users to determine which LLM best suits their particular needs. To address these issues, we propose to evaluate LLMs from a user-centric perspective and design this benchmark to measure their efficacy in satisfying user needs under distinct intents. Firstly, we collect 1,846 real-world use cases from a user study with 712 participants from 23 countries. This first-hand data helps us understand actual user intents and needs in LLM interactions, forming the User Reported Scenarios (URS) dataset, which is categorized with six types of user intents. Secondly, based on this authentic dataset, we benchmark 10 LLM services with GPT-4-as-Judge. Thirdly, we show that benchmark scores align well with human preference in both real-world experience and pair-wise annotations, achieving Pearson correlations of 0.95 and 0.94, respectively. This alignment confirms that the URS dataset and our evaluation method establish an effective user-centric benchmark. The dataset, code, and process data are publicly available at https://github.com/Alice1998/URS.

pdf bib
Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Yuang Li | Min Zhang | Mengxin Ren | Xiaosong Qiao | Miaomiao Ma | Daimeng Wei | Hao Yang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. However, the existing ADD datasets are outdated, leading to suboptimal generalization of detection models. In this paper, we construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models. To simulate real-world scenarios, we employ diverse attack methods and audio prompts from different datasets. Experiments show that, through novel attack-augmented training, the Wav2Vec2-large and Whisper-medium models achieve equal error rates of 4.1% and 6.5% respectively. Additionally, we demonstrate our models’ outstanding few-shot ADD ability by fine-tuning with just one minute of target-domain data. Nonetheless, neural codec compressors greatly affect the detection accuracy, necessitating further research. Our dataset is publicly available (https://github.com/leolya/CD-ADD).

pdf bib
Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
Siqi Wang | Zhengyu Chen | Bei Li | Keqing He | Min Zhang | Jingang Wang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

The scaling of large language models (LLMs) is a critical research area for the efficiency and effectiveness of model training and deployment. Our work investigates the transferability and discrepancies of scaling laws between Dense Models and Mixture of Experts (MoE) models. Through a combination of theoretical analysis and extensive experiments, including consistent loss scaling, optimal batch size/learning rate scaling, and resource allocation strategies scaling, our findings reveal that the power-law scaling framework also applies to MoE Models, indicating that the fundamental principles governing the scaling behavior of these models are preserved, even though the architecture differs. Additionally, MoE Models demonstrate superior generalization, resulting in lower testing losses with the same training compute budget compared to Dense Models. These findings indicate the scaling consistency and transfer generalization capabilities of MoE Models, providing new insights for optimizing MoE Model training and deployment strategies.

pdf bib
CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions
Jun Rao | Xuebo Liu | Lian Lian | Shengjun Cheng | Yunjie Liao | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands. Diverging from most works focusing on data mixing, our study concentrates on enhancing the model’s capabilities from the perspective of data sampling during training. Drawing inspiration from the human learning process, where it is generally easier to master solutions to similar topics through focused practice on a single type of topic, we introduce a novel instruction tuning strategy termed CommonIT: Commonality-aware Instruction Tuning. Specifically, we cluster instruction datasets into distinct groups with three proposed metrics Task, Embedding and Length). We ensure each training mini-batch, or “partition”, consists solely of data from a single group, which brings about both data randomness across mini-batches and intra-batch data similarity. Rigorous testing on LLaMa models demonstrates CommonIT’s effectiveness in enhancing the instruction-following capabilities of LLMs through IT datasets (FLAN, CoT, and Alpaca) and models (LLaMa2-7B, Qwen2-7B, LLaMa 13B, and BLOOM 7B). CommonIT consistently boosts an average improvement of 2.1% on the general domain (i.e., the average score of Knowledge, Reasoning, Multilinguality and Coding) with the Length metric, and 5.2% on the special domain (i.e., GSM, Openfunctions and Code) with the Task metric, and 3.8% on the specific tasks (i.e., MMLU) with the Embedding metric. Code is available at https://github.com/raojay7/CommonIT.

pdf bib
Self-Powered LLM Modality Expansion for Large Speech-Text Models
Tengfei Yu | Xuebo Liu | Zhiyi Hou | Liang Ding | Dacheng Tao | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Large language models (LLMs) exhibit remarkable performance across diverse tasks, indicating their potential for expansion into large speech-text models (LSMs) by integrating speech capabilities. Although unified speech-text pre-training and multimodal data instruction-tuning offer considerable benefits, these methods generally entail significant resource demands and tend to overfit specific tasks.This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning. We explore the instruction-following dynamics within LSMs, identifying a critical issue termed speech anchor bias—a tendency for LSMs to over-rely on speech inputs, mistakenly interpreting the entire speech modality as directives, thereby neglecting textual instructions.To counteract this bias, we introduce a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning. Our experiments across a range of speech-based tasks demonstrate that self-powered LSM mitigates speech anchor bias and improves the fusion of speech and text modalities in LSMs. Data, code and scripts are freely available at https://github.com/ytf-philp/Self-powered-LSM.

pdf bib
Curriculum Consistency Learning for Conditional Sentence Generation
Liangxin Liu | Xuebo Liu | Lian Lian | Shengjun Cheng | Jun Rao | Tengfei Yu | Hexuan Deng | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Consistency learning (CL) has proven to be a valuable technique for improving the robustness of models in conditional sentence generation (CSG) tasks by ensuring stable predictions across various input data forms. However, models augmented with CL often face challenges in optimizing consistency features, which can detract from their efficiency and effectiveness. To address these challenges, we introduce Curriculum Consistency Learning (CCL), a novel strategy that guides models to learn consistency in alignment with their current capacity to differentiate between features. CCL is designed around the inherent aspects of CL-related losses, promoting task independence and simplifying implementation. Implemented across four representative CSG tasks, including instruction tuning (IT) for large language models and machine translation (MT) in three modalities (text, speech, and vision), CCL demonstrates marked improvements. Specifically, it delivers +2.0 average accuracy point improvement compared with vanilla IT and an average increase of +0.7 in COMET scores over traditional CL methods in MT tasks. Our comprehensive analysis further indicates that models utilizing CCL are particularly adept at managing complex instances, showcasing the effectiveness and efficiency of CCL in improving CSG models. Code and scripts are available at https://github.com/xinxinxing/Curriculum-Consistency-Learning.

pdf bib
A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models
Houquan Zhou | Zhenghua Li | Bo Zhang | Chen Li | Shaopeng Lai | Ji Zhang | Fei Huang | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

This work proposes a simple training-free prompt-free approach to leverage large language models (LLMs) for the Chinese spelling correction (CSC) task, which is totally different from all previous CSC approaches. The key idea is to use an LLM as a pure language model in a conventional manner. The LLM goes through the input sentence from the beginning, and at each inference step, produces a distribution over its vocabulary for deciding the next token, given a partial sentence. To ensure that the output sentence remains faithful to the input sentence, we design a minimal distortion model that utilizes pronunciation or shape similarities between the original and replaced characters. Furthermore, we propose two useful reward strategies to address practical challenges specific to the CSC task. Experiments on five public datasets demonstrate that our approach significantly improves LLM performance, enabling them to compete with state-of-the-art domain-general CSC models.

pdf bib
DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators
Xinglin Lyu | Junhui Li | Yanqing Zhao | Min Zhang | Daimeng Wei | Shimin Tao | Hao Yang | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

pdf bib
DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators
Xinglin Lyu | Junhui Li | Yanqing Zhao | Min Zhang | Daimeng Wei | Shimin Tao | Hao Yang | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

pdf bib
Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner
Shudong Liu | Zhaocong Li | Xuebo Liu | Runzhe Zhan | Derek F. Wong | Lidia S. Chao | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Large language models (LLMs) often exhibit excessive, random, and uninformative uncertainty, rendering them unsuitable for decision-making in human-computer interactions. In this paper, we aim to instigate a heightened awareness of self-uncertainty in LLMs, enabling them to express uncertainty more effectively. To accomplish this, we propose an uncertainty-aware instruction tuning (UaIT) method, aligning LLMs’ perception with the probabilistic uncertainty of the generation. We conducted experiments using LLaMA2 and Mistral on multiple free-form QA tasks. Experimental results revealed a surprising 45.2% improvement in the effectiveness of uncertainty expression by LLMs, accompanied by reasonably good out-of-domain generalization capabilities. Moreover, this uncertainty expression can serve as a valuable real-time basis for human decision-making, e.g., retrieving external documents and incorporating stronger LLMs.

pdf bib
Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Xinping Zhao | Jindi Yu | Zhenyu Liu | Jifang Wang | Dongfang Li | Yibin Chen | Baotian Hu | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

As we all know, hallucinations prevail in Large Language Models (LLMs), where the generated content is coherent but factually incorrect, which inflicts a heavy blow on the widespread application of LLMs. Previous studies have shown that LLMs could confidently state non-existent facts rather than answering “I don’t know”. Therefore, it is necessary to resort to external knowledge to detect and correct the hallucinated content. Since manual detection and correction of factual errors is labor-intensive, developing an automatic end-to-end hallucination-checking approach is indeed a needful thing. To this end, we present Medico, a Multi-source evidence fusion enhanced hallucination detection and correction framework. It fuses diverse evidence from multiple sources, detects whether the generated content contains factual errors, provides the rationale behind the judgment, and iteratively revises the hallucinated content. Experimental results on evidence retrieval (0.964 HR@5, 0.908 MRR@5), hallucination detection (0.927-0.951 F1), and hallucination correction (0.973-0.979 approval rate) manifest the great potential of Medico. A video demo of Medico can be found at https://youtu.be/RtsO6CSesBI.

pdf bib
TruthReader: Towards Trustworthy Document Assistant Chatbot with Reliable Attribution
Dongfang Li | Xinshuo Hu | Zetian Sun | Baotian Hu | Shaolin Ye | Zifei Shan | Qian Chen | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Document assistant chatbots are empowered with extensive capabilities by Large Language Models (LLMs) and have exhibited significant advancements. However, these systems may suffer from hallucinations that are difficult to verify in the context of given documents.Moreover, despite the emergence of products for document assistants, they either heavily rely on commercial LLM APIs or lack transparency in their technical implementations, leading to expensive usage costs and data privacy concerns. In this work, we introduce a fully open-source document assistant chatbot with reliable attribution, named TruthReader, utilizing adapted conversational retriever and LLMs. Our system enables the LLMs to generate answers with detailed inline citations, which can be attributed to the original document paragraphs, facilitating the verification of the factual consistency of the generated text. To further adapt the generative model, we develop a comprehensive pipeline consisting of data construction and model optimization processes.This pipeline equips the LLMs with the necessary capabilities to generate accurate answers, produce reliable citations, and refuse unanswerable questions. Our codebase, data and models are released, and the video demonstration of our system is available at https://youtu.be/RYVt3itzUQM.

pdf bib
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
Xin Zhang | Yanzhao Zhang | Dingkun Long | Wen Xie | Ziqi Dai | Jialong Tang | Huan Lin | Baosong Yang | Pengjun Xie | Fei Huang | Meishan Zhang | Wenjie Li | Min Zhang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track

We present systematic efforts in building long-context multilingual text representation model (TRM) and reranker from scratch for text retrieval. We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in a native 8192-token context (longer than 512 of previous multilingual encoders). Then we construct a hybrid TRM and a cross-encoder reranker by contrastive learning. Evaluations show that our text encoder outperforms the same-sized previous state-of-the-art XLM-R. Meanwhile, our TRM and reranker match the performance of large-sized state-of-the-art BGE-M3 models and achieve better results on long-context retrieval benchmarks. Further analysis demonstrate that our proposed models exhibit higher efficiency during both training and inference. We believe their efficiency and effectiveness could benefit various researches and industrial applications.

pdf bib
Retrieval-style In-context Learning for Few-shot Hierarchical Text Classification
Huiyao Chen | Yu Zhao | Zulong Chen | Mengjia Wang | Liangyue Li | Meishan Zhang | Min Zhang
Transactions of the Association for Computational Linguistics, Volume 12

Hierarchical text classification (HTC) is an important task with broad applications, and few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Particularly, we equip the retrieval database with HTC label-aware representations for the input texts, which is achieved by continual training on a pretrained language model with masked language modeling (MLM), layer-wise classification (CLS, specifically for HTC), and a novel divergent contrastive learning (DCL, mainly for adjacent semantically similar labels) objective. Experimental results on three benchmark datasets demonstrate superior performance of our method, and we can achieve state-of-the-art results in few-shot HTC.

pdf bib
HW-TSC at TextGraphs-17 Shared Task: Enhancing Inference Capabilities of LLMs with Knowledge Graphs
Wei Tang | Xiaosong Qiao | Xiaofeng Zhao | Min Zhang | Chang Su | Yuang Li | Yinglu Li | Yilun Liu | Feiyu Yao | Shimin Tao | Hao Yang | He Xianghui
Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing

In this paper, we present an effective method for TextGraphs-17 Shared Task. This task requires selecting an entity from the candidate entities that is relevant to the given question and answer. The selection process is aided by utilizing the shortest path graph in the knowledge graph, connecting entities in the query to the candidate entity. This task aims to explore how to enhance LLMs output with KGs, although current LLMs have certain logical reasoning capabilities, they may not be certain about their own outputs, and the answers they produce may be correct by chance through incorrect paths. In this case, we have introduced a LLM prompt design strategy based on self-ranking and emotion. Specifically, we let the large model score its own answer choices to reflect its confidence in the answer. Additionally, we add emotional incentives to the prompts to encourage the model to carefully examine the questions. Our submissions was conducted under zero-resource setting, and we achieved the second place in the task with an F1-score of 0.8321.

pdf bib
Chinese Spoken Named Entity Recognition in Real-world Scenarios: Dataset and Approaches
Shilin Zhou | Zhenghua Li | Chen Gong | Lei Zhang | Yu Hong | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Spoken Named Entity Recognition (NER) aims to extract entities from speech. The extracted entities can help voice assistants better understand user’s questions and instructions. However, current Chinese Spoken NER datasets are laboratory-controlled data that are collected by reading existing texts in quiet environments, rather than natural spoken data, and the texts used for reading are also limited in topics. These limitations obstruct the development of Spoken NER in more natural and common real-world scenarios. To address this gap, we introduce a real-world Chinese Spoken NER dataset (RWCS-NER), encompassing open-domain daily conversations and task-oriented intelligent cockpit instructions. We compare several mainstream pipeline approaches on RWCS-NER. The results indicate that the current methods, affected by Automatic Speech Recognition (ASR) errors, do not perform satisfactorily in real settings. Aiming to enhance Spoken NER in real-world scenarios, we propose two approaches: self-training-asr and mapping then distilling (MDistilling). Experiments show that both approaches can achieve significant improvements, particularly MDistilling. Even compared with GPT4.0, MDistilling still reaches better results. We believe that our work will advance the field of Spoken NER in real-world settings.

pdf bib
From Role-Play to Drama-Interaction: An LLM Solution
Weiqi Wu | Hongqiu Wu | Lai Jiang | Xingyuan Liu | Hai Zhao | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Drama is a form of storytelling inspired by human creativity, proceeding with a predefined storyline, carrying emotions and thoughts.This paper introduces LLM-based interactive drama, which endows traditional drama with an unprecedented immersion, where a person is allowed to walk into it and interact with the characters and scenes.We define this new artistic genre by 6 essential elements—plot, character, thought, diction, spectacle and interaction—and study the entire pipeline to forge a backbone drama LLM to drive the playing process, which is challenged by limited drama resources, uncontrollable narrative development, and complicated instruction following.We propose Narrative Chain to offer finer control over the narrative progression during interaction with players;Auto-Drama to synthesize drama scripts given arbitrary stories;Sparse Instruction Tuning to allow the model to follow sophisticated instructions.We manually craft 3 scripts, Detective Conan, Harry Potter, Romeo and Juliet, and design a 5-dimension principle to evaluate the drama LLM comprehensively.

pdf bib
Rethinking Negative Instances for Generative Named Entity Recognition
Yuyang Ding | Juntao Li | Pinzheng Wang | Zecheng Tang | Yan Bowen | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Large Language Models (LLMs) have demonstrated impressive capabilities for generalizing in unseen tasks. In the Named Entity Recognition (NER) task, recent advancements have seen the remarkable improvement of LLMs in a broad range of entity domains via instruction tuning, by adopting entity-centric schema. In this work, we explore the potential enhancement of the existing methods by incorporating negative instances into training. Our experiments reveal that negative instances contribute to remarkable improvements by (1) introducing contextual information, and (2) clearly delineating label boundaries. Furthermore, we introduce an efficient longest common subsequence (LCS) matching algorithm, which is tailored to transform unstructured predictions into structured entities. By integrating these components, we present GNER, a Generative NER system that shows improved zero-shot performance across unseen entity domains. Our comprehensive evaluation illustrates our system’s superiority, surpassing state-of-the-art (SoTA) methods by 9 F1 score in zero-shot evaluation.

pdf bib
Improving Attributed Text Generation of Large Language Models via Preference Learning
Dongfang Li | Zetian Sun | Baotian Hu | Zhenyu Liu | Xinshuo Hu | Xuebo Liu | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means to provide evidence (i.e., citations). However, current attribution methods usually focus on the retrieval stage and automatic evaluation that neglect mirroring the citation mechanisms in human scholarly writing to bolster credibility. In this paper, we address these challenges by modelling the attribution task as preference learning and introducing an Automatic Preference Optimization (APO) framework. First, we create a curated collection for post-training with 6,330 examples by collecting and filtering from existing datasets. Second, considering the high cost of labelling preference data, we further propose an automatic method to synthesize attribution preference data resulting in 95,263 pairs. Moreover, inspired by the human citation process, we further propose a progressive preference optimization method by leveraging fine-grained information. Extensive experiments on three datasets (i.e., ASQA, StrategyQA, and ELI5) demonstrate that APO achieves state-of-the-art citation F1 with higher answer quality.

pdf bib
Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation
Zhibin Lan | Liqiang Niu | Fandong Meng | Jie Zhou | Min Zhang | Jinsong Su
Findings of the Association for Computational Linguistics: ACL 2024

pdf bib
Chinese Spelling Corrector Is Just a Language Learner
Lai Jiang | Hongqiu Wu | Hai Zhao | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

This paper emphasizes Chinese spelling correction by means of self-supervised learning, which means there are no annotated errors within the training data. Our intuition is that humans are naturally good correctors with exposure to error-free sentences, which contrasts with current unsupervised methods that strongly rely on the usage of confusion sets to produce parallel sentences. In this paper, we demonstrate that learning a spelling correction model is identical to learning a language model from error-free data alone, with decoding it in a greater search space. We propose Denoising Decoding Correction (D2C), which selectively imposes noise upon the source sentence to determine the underlying correct characters. Our method is largely inspired by the ability of language models to perform correction, including both BERT-based models and large language models (LLMs). We show that the self-supervised learning manner generally outperforms the confusion set in specific domains because it bypasses the need to introduce error characters to the training data which can impair the error patterns not included in the introduced error characters.

pdf bib
Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval
Yan Gao | Zhiwei Cao | Zhongjian Miao | Baosong Yang | Shiyu Liu | Min Zhang | Jinsong Su
Findings of the Association for Computational Linguistics: ACL 2024

To achieve non-parametric NMT domain adaptation, k-Nearest-Neighbor Machine Translation (kNN-MT) constructs an external datastore to store domain-specific translation knowledge, which derives a kNN distribution to interpolate the prediction distribution of the NMT model via a linear interpolation coefficient 𝜆. Despite its success, kNN retrieval at each timestep leads to substantial time overhead. To address this issue, dominant studies resort to kNN-MT with adaptive retrieval (kNN-MT-AR), which dynamically estimates 𝜆 and skips kNN retrieval if 𝜆 is less than a fixed threshold. Unfortunately, kNN-MT-AR does not yield satisfactory results. In this paper, we first conduct a preliminary study to reveal two key limitations of kNN-MT-AR: 1) the optimization gap leads to inaccurate estimation of 𝜆 for determining kNN retrieval skipping, and 2) using a fixed threshold fails to accommodate the dynamic demands for kNN retrieval at different timesteps. To mitigate these limitations, we then propose kNN-MT with dynamic retrieval (kNN-MT-DR) that significantly extends vanilla kNN-MT in two aspects. Firstly, we equip kNN-MT with a MLP-based classifier for determining whether to skip kNN retrieval at each timestep. Particularly, we explore several carefully-designed scalar features to fully exert the potential of the classifier. Secondly, we propose a timestep-aware threshold adjustment method to dynamically generate the threshold, which further improves the efficiency of our model. Experimental results on the widely-used datasets demonstrate the effectiveness and generality of our model.

pdf bib
DB-LLM: Accurate Dual-Binarization for Efficient LLMs
Hong Chen | Chengtao Lv | Liang Ding | Haotong Qin | Xiabin Zhou | Yifu Ding | Xuebo Liu | Min Zhang | Jinyang Guo | Xianglong Liu | Dacheng Tao
Findings of the Association for Computational Linguistics: ACL 2024

Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment. Quantization emerges as one of the most effective methods for improving the computational efficiency of LLMs. However, existing ultra-low-bit quantization always causes severe accuracy drops. In this paper, we empirically investigate the micro and macro characteristics of ultra-low bit quantization and present a novel Dual-Binarization method for LLMs, namely DB-LLM. For the micro-level, we take both the accuracy advantage of 2-bit-width and the efficiency advantage of binarization into account, introducing Flexible Dual Binarization (FDB). By splitting 2-bit quantized weights into two independent sets of binaries, FDB ensures the accuracy of representations and introduces flexibility, utilizing the efficient bitwise operations of binarization while retaining the inherent high sparsity of ultra-low bit quantization. For the macro-level, we find the distortion that exists in the prediction of LLM after quantization, which is specified as the deviations related to the ambiguity of samples. We propose the Deviation-Aware Distillation (DAD) method, enabling the model to focus differently on various samples. Comprehensive experiments show that our DB-LLM not only significantly surpasses the current State-of-The-Art (SoTA) in ultra-low bit quantization (, perplexity decreased from 9.64 to 7.23), but also achieves an additional 20% reduction in computational consumption compared to the SOTA method under the same bit-width. Our code is available at https://github.com/Hon-Chen/DB-LLM.

pdf bib
Semantic Role Labeling from Chinese Speech via End-to-End Learning
Huiyao Chen | Xinxin Li | Meishan Zhang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Semantic Role Labeling (SRL), crucial for understanding semantic relationships in sentences, has traditionally focused on text-based input. However, the increasing use of voice assistants and the need for hands-free interaction have highlighted the importance of SRL from speech.SRL from speech can be accomplished via a two-step pipeline directly: transcribing speech to text via Automatic Speech Recognition (ASR) and then applying text-based SRL, which could lead to error propagation and loss of useful acoustic features.Addressing these challenges, we present the first end-to-end approach for SRL from speech, integrating ASR and SRL in a joint-learning framework, focusing on the Chinese language. By employing a Stright-Through Gumbel-Softmax module for connecting ASR and SRL models, it enables gradient back-propagation and joint optimization, enhancing robustness and effectiveness.Experiments on the Chinese Proposition Bank 1.0 (CPB1.0) and a newly annotated dataset AS-SRL based on AISHELL-1 demonstrate the superiority of the end-to-end model over traditional pipelines, with significantly improved performance.

pdf bib
CTC-based Non-autoregressive Textless Speech-to-Speech Translation
Qingkai Fang | Zhengrui Ma | Yan Zhou | Min Zhang | Yang Feng
Findings of the Association for Computational Linguistics: ACL 2024

Direct speech-to-speech translation (S2ST) has achieved impressive translation quality, but it often faces the challenge of slow decoding due to the considerable length of speech sequences. Recently, some research has turned to non-autoregressive (NAR) models to expedite decoding, yet the translation quality typically lags behind autoregressive (AR) models significantly. In this paper, we investigate the performance of CTC-based NAR models in S2ST, as these models have shown impressive results in machine translation. Experimental results demonstrate that by combining pretraining, knowledge distillation, and advanced NAR training techniques such as glancing training and non-monotonic latent alignments, CTC-based NAR models achieve translation quality comparable to the AR model, while preserving up to 26.81× decoding speedup.

pdf bib
Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation
Zhexuan Wang | Shudong Liu | Xuebo Liu | Miao Zhang | Derek Wong | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

kNN-MT has utilized neighborhood knowledge for auxiliary decoding, significantly improving translation performance. Subsequently, kNN-KD transitions the use of neighborhood knowledge from the decoding phase to the training phase, to address the temporal and spatial inefficiencies inherent in kNN-MT. However, kNN-KD transfers all the kNN knowledge arbitrarily, which has the potential to restrict the learning of student models. In this paper, we propose a novel domain-aware kNN-KD method, which filters out domain-relevant neighborhood knowledge for learning in the distillation process. Notably, this entire process exclusively utilizes the neighborhood knowledge of the original model, eliminating the need for establishing any additional datastores. Experiments on four domain translation tasks demonstrate that our method achieves state-of-the-art performance, realizing an average gain of 1.55 COMET and 1.42 BLEU scores, by further enhancing the translation of rare words. Source code can be accessed at https://github.com/wangzx1219/Dk-KD.

pdf bib
A Two-Stage Adaptation of Large Language Models for Text Ranking
Longhui Zhang | Yanzhao Zhang | Dingkun Long | Pengjun Xie | Meishan Zhang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Text ranking is a critical task in information retrieval. Recent advances in pre-trained language models (PLMs), especially large language models (LLMs), present new opportunities for applying them to text ranking. While supervised fine-tuning (SFT) with ranking data has been widely explored to better align PLMs with text ranking goals, previous studies have focused primarily on encoder-only and encoder-decoder PLMs. Research on leveraging decoder-only LLMs for text ranking remains scarce. An exception to this is RankLLaMA, which uses direct SFT to explore LLaMA’s potential for text ranking. In this work, we propose a two-stage progressive paradigm to better adapt LLMs to text ranking. First, we conduct continual pre-training (CPT) of LLMs on a large weakly-supervised corpus. Second, we perform SFT, and propose an improved optimization strategy building upon RankLLaMA. Our experimental results on multiple benchmarks show that our approach outperforms previous methods in both in-domain and out-domain scenarios.

pdf bib
Efficient Domain Adaptation for Non-Autoregressive Machine Translation
WangJie You | Pei Guo | Juntao Li | Kehai Chen | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Domain adaptation remains a challenge in the realm of Neural Machine Translation (NMT), even in the era of large language models (LLMs). Existing non-parametric approaches like nearest neighbor machine translation have made small Autoregressive Translation (AT) models achieve efficient domain generalization and adaptation without updating parameters, but leaving the Non-Autoregressive Translation (NAT) counterparts under-explored. To fill this blank, we introduce Bi-kNN, an innovative and efficient domain adaptation approach for NAT models that tailors a k-nearest-neighbor algorithm for NAT. Specifically, we introduce an effective datastore construction and correlated updating strategies to conform the parallel nature of NAT. Additionally, we train a meta-network that seamlessly integrates the NN distribution with the NMT distribution robustly during the iterative decoding process of NAT. Our experimental results across four benchmark datasets demonstrate that our Bi-kNN not only achieves significant improvements over the Base-NAT model (7.8 BLEU on average) but also exhibits enhanced efficiency.

pdf bib
Exploring Reversal Mathematical Reasoning Ability for Large Language Models
Pei Guo | WangJie You | Juntao Li | Yan Bowen | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Large language models (LLMs) have presented remarkable capabilities in the wide range of natural language understanding and reasoning tasks. Despite their success, a few works indicate that LLMs suffer from the “reversal curse”, in which LLMs can’t employ the inverted structure “B is A” when they are trained based on “A is B”. To explore the effect of the “reversal curse” for LLMs on complex mathematical reasoning tasks, we present two reversal datasets upon GSM8K and MathQA and verify that LLMs also struggle to solve reversal mathematical problems. We analyze the potential reason and attribute it to the insufficient modeling of the relationship between reasoning steps caused by the left-to-right objective. Consequently, based on the characteristics of multi-step reasoning, we design a novel training method to improve the general and reversal reasoning abilities. Finally, we conduct experiments on four mathematical datasets, and the results demonstrate that our method significantly improves the general reasoning capacities and alleviates the reversal problem. Our datasets and codes are available at https: //github.com/AllForward/ReversalMath.

pdf bib
Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
Hongbin Zhang | Kehai Chen | Xuefeng Bai | Yang Xiang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Large language models (LLMs) have showcased their remarkable capabilities to handle various downstream tasks, including multilingual machine translation ability. Despite their impressive performance, decoder-only LLMs lack an explicit alignment between source and target contexts, leading to translation that may not faithfully represent the original content. To address this, we propose three learning strategies to encourage LLMs to pay more attention to the source context during translation: 1) adjusting attention weights on the source context by adaptive attention re-weighting; 2) suppressing the irrelevant target prefix using contrastive decoding; 3) avoiding excessive reliance on the target prefix through target-constrained tuning. To verify the effectiveness of our model, we curate a new dataset specifically focusing on unfaithful translations generated by LLMs. Experimental results on both human-collected and general test sets verify the effectiveness of our model across multiple language pairs. Further human evaluation demonstrates the efficacy of our method in reducing hallucinatory translation and improving the fidelity of translations.

pdf bib
Towards Demonstration-Aware Large Language Models for Machine Translation
Chen Li | Meishan Zhang | Xuebo Liu | Zhaocong Li | Derek Wong | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Tuning-based large language models for machine translation (aka large translation model, LTM) have demonstrated significant performance in the field of machine translation. Despite their success, these models often face difficulties in leveraging demonstrations to further improve their performance. To tackle this challenge, we introduce a novel approach that integrates demonstration-aware training and inference strategies within the framework of tuning-based LTMs, hereby referred to as demonstration-aware LTMs. During training, we enrich the model’s learning process by incorporating both sentence- and document-level demonstrations derived from its original training dataset. During inference, the model synergizes its own contextual translations with retrieved high-quality demonstrations, leading to more precise and contextually appropriate outputs. Empirical results reveal that our demonstration-aware LTM not only mitigates the negative impacts traditionally associated with demonstrations but also secures substantial improvements in translation accuracy, particularly in domain-specific and document-level translation tasks. Source code and scripts are freely available at https://github.com/ChenLi0620/Demo-Aware-LLM-MT.

pdf bib
Unsupervised Sign Language Translation and Generation
Zhengsheng Guo | Zhiwei He | Wenxiang Jiao | Xing Wang | Rui Wang | Kehai Chen | Zhaopeng Tu | Yong Xu | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without parallel sign language data. USLNet comprises two main components: single-modality reconstruction modules (text and video) that rebuild the input from its noisy version in the same modality and cross-modality back-translation modules (text-video-text and video-text-video) that reconstruct the input from its noisy version in the different modality using back-translation procedure. Unlike the single-modality back-translation procedure in text-based UNMT, USLNet faces the cross-modality discrepancy in feature representation, in which the length and the feature dimension mismatch between text and video sequences. We propose a sliding window method to address the issues of aligning variable-length text with video sequences. To our knowledge, USLNet is the first unsupervised sign language translation and generation model capable of generating both natural language text and sign language video in a unified manner. Experimental results on the BBC-Oxford Sign Language dataset and Open-Domain American Sign Language dataset reveal that USLNet achieves competitive results compared to supervised baseline models, indicating its effectiveness in sign language translation and generation.

pdf bib
Demonstration Augmentation for Zero-shot In-context Learning
Yi Su | Yunpeng Tai | Yixin Ji | Juntao Li | Yan Bowen | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates.However, many studies have highlighted that the model’s performance is sensitive to the choice of demonstrations, presenting a significant challenge for practical applications where we lack prior knowledge of user queries.Consequently, we need to construct an extensive demonstration pool and incorporate external databases to assist the model, leading to considerable time and financial costs.In light of this, some recent research has shifted focus towards zero-shot ICL, aiming to reduce the model’s reliance on external information by leveraging their inherent generative capabilities. Despite the effectiveness of these approaches, the content generated by the model may be unreliable, and the generation process is time-consuming.To address these issues, we propose Demonstration Augmentation for In-context Learning (DAIL), which employs the model’s previously predicted historical samples as demonstrations for subsequent ones.DAIL brings no additional inference cost and does not rely on the model’s generative capabilities.Our experiments reveal that DAIL can significantly improve the model’s performance over direct zero-shot inference and can even outperform few-shot ICL without any external information.

pdf bib
Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction
Meishan Zhang | Hao Fei | Bin Wang | Shengqiong Wu | Yixin Cao | Fei Li | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2024

In the field of information extraction (IE), tasks across a wide range of modalities and their combinations have been traditionally studied in isolation, leaving a gap in deeply recognizing and analyzing cross-modal information. To address this, this work for the first time introduces the concept of grounded Multimodal Universal Information Extraction (MUIE), providing a unified task framework to analyze any IE tasks over various modalities, along with their fine-grained groundings. To tackle MUIE, we tailor a multimodal large language model (MLLM), Reamo, capable of extracting and grounding information from all modalities, i.e., recognizing everything from all modalities at once. Reamo is updated via varied tuning strategies, equipping it with powerful capabilities for information recognition and fine-grained multimodal grounding. To address the absence of a suitable benchmark for grounded MUIE, we curate a high-quality, diverse, and challenging test set, which encompasses IE tasks across 9 common modality combinations with the corresponding multimodal groundings. The extensive comparison of Reamo with existing MLLMs integrated into pipeline approaches demonstrates its advantages across all evaluation dimensions, establishing a strong benchmark for the follow-up research. Our resources are publicly released at https://haofei.vip/MUIE.

pdf bib
Concise and Precise Context Compression for Tool-Using Language Models
Yang Xu | Yunlong Feng | Honglin Mu | Yutai Hou | Yitong Li | Xinghao Wang | Wanjun Zhong | Zhongyang Li | Dandan Tu | Qingfu Zhu | Min Zhang | Wanxiang Che
Findings of the Association for Computational Linguistics: ACL 2024

Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy documentation every time the model needs to use the tool, occupying the input window as well as slowing down the decoding process.Given the progress in general-purpose compression, soft context compression is a suitable approach to alleviate the problem. However, when compressing tool documentation, existing methods suffer from the weaknesses of key information loss (specifically, tool/parameter name errors) and difficulty in adjusting the length of compressed sequences based on documentation lengths.To address these problems, we propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models. 1) Selective compression strategy mitigates key information loss by deliberately retaining key information as raw text tokens. 2) Block compression strategy involves dividing tool documentation into short chunks and then employing a fixed-length compression model to achieve variable-length compression. This strategy facilitates the flexible adjustment of the compression ratio.Results on API-Bank and APIBench show that our approach reaches a performance comparable to the upper-bound baseline under up to 16x compression ratio.

pdf bib
Dynamic Planning for LLM-based Graphical User Interface Automation
Shaoqing Zhang | Zhuosheng Zhang | Kehai Chen | Xinbei Ma | Muyun Yang | Tiejun Zhao | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2024

The advent of large language models (LLMs) has spurred considerable interest in advancing autonomous LLMs-based agents, particularly in intriguing applications within smartphone graphical user interfaces (GUIs). When presented with a task goal, these agents typically emulate human actions within a GUI environment until the task is completed. However, a key challenge lies in devising effective plans to guide action prediction in GUI tasks, though planning have been widely recognized as effective for decomposing complex tasks into a series of steps. Specifically, given the dynamic nature of environmental GUIs following action execution, it is crucial to dynamically adapt plans based on environmental feedback and action history.We show that the widely-used ReAct approach fails due to the excessively long historical dialogues. To address this challenge, we propose a novel approach called Dynamic Planning of Thoughts (D-PoT) for LLM-based GUI agents.D-PoT involves the dynamic adjustment of planning based on the environmental feedback and execution history. Experimental results reveal that the proposed D-PoT significantly surpassed the strong GPT-4V baseline by +12.7% (34.66% 47.36%) in accuracy. The analysis highlights the generality of dynamic planning in different backbone LLMs, as well as the benefits in mitigating hallucinations and adapting to unseen tasks. Code is available at https://github.com/sqzhang-lazy/D-PoT.

pdf bib
MultiSkill: Evaluating Large Multimodal Models for Fine-grained Alignment Skills
Zhenran Xu | Senbao Shi | Baotian Hu | Longyue Wang | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2024

We propose MultiSkill, an evaluation protocol that assesses large multimodal models (LMMs) across multiple fine-grained skills for alignment with human values. Recent LMMs have shown various intriguing abilities, such as solving graph theory problems and explaining visual jokes. However, existing multimodal benchmarks have mainly focused on coarse-grained evaluation (e.g., accuracy), without considering the skill composition required by specific instructions. To this end, we present MultiSkill, designed to decompose coarse-level scoring to a fine-grained skill set-level scoring tailored to each instruction. MultiSkill defines five core vision-language capabilities and divides into 12 skills that are necessary to align with user instructions. For evaluation metrics on specific skills, we propose an LMM-based evaluator for open-ended outputs. Based on the diverse instructions collected from 66 datasets spanning 10 domains, we compare multiple representative open-source and proprietary LMMs and find a high correlation between model-based and human-based evaluations. Our experiments underscore the importance of fine-grained evaluation in providing a holistic view of model performance and enhancing the reliability of the evaluation.

pdf bib
Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization
Yixin Ji | Yang Xiang | Juntao Li | Qingrong Xia | Zi Ye | Xinyu Duan | Zhefeng Wang | Kehai Chen | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2024

In recent years, large language models (LLMs) have driven advances in natural language processing. Still, their growing scale has increased the computational burden, necessitating a balance between efficiency and performance. Low-rank compression, a promising technique, reduces non-essential parameters by decomposing weight matrices into products of two low-rank matrices. Yet, its application in LLMs has not been extensively studied. The key to low-rank compression lies in low-rank factorization and low-rank dimensions allocation. To address the challenges of low-rank compression in LLMs, we conduct empirical research on the low-rank characteristics of large models. We propose a low-rank compression method suitable for LLMs. This approach involves precise estimation of feature distributions through pooled covariance matrices and a Bayesian optimization strategy for allocating low-rank dimensions. Experiments on the LLaMA-2 models demonstrate that our method outperforms existing strong structured pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

pdf bib
Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering
Yixin Ji | Kaixin Wu | Juntao Li | Wei Chen | Mingjie Zhong | Xu Jia | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2024

Despite Large Language Models (LLMs) have performed impressively in various Natural Language Processing (NLP) tasks, their inherent hallucination phenomena severely challenge their credibility in complex reasoning. Combining explainable Knowledge Graphs (KGs) with LLMs is a promising path to address this issue. However, structured KGs are difficult to utilize, and how to make LLMs understand and incorporate them is a challenging topic. We thereby reorganize a more efficient structure of KGs, while designing the KG-related instruction tuning and continual pre-training strategies to enable LLMs to learn and internalize this form of representation effectively. Moreover, we construct subgraphs to further enhance the retrieval capabilities of KGs via CoT reasoning. Extensive experiments on two KGQA datasets demonstrate that our model achieves convincing performance compared to strong baselines.

pdf bib
Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering
Yu Zhang | Kehai Chen | Xuefeng Bai | Zhao Kang | Quanjiang Guo | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2024

Knowledge graph question answering (KGQA) involves answering natural language questions by leveraging structured information stored in a knowledge graph. Typically, KGQA initially retrieve a targeted subgraph from a large-scale knowledge graph, which serves as the basis for reasoning models to address queries. However, the retrieved subgraph inevitably brings distraction information for knowledge utilization, impeding the model’s ability to perform accurate reasoning. To address this issue, we propose a Question-guided Knowledge Graph Re-scoring method (Q-KGR) to eliminate noisy pathways for the input question, thereby focusing specifically on pertinent factual knowledge.Moreover, we introduce Knowformer, a parameter-efficient method for injecting the re-scored knowledge graph into large language models to enhance their ability to perform factual reasoning.Extensive experiments on multiple KGQA benchmarks demonstrate the superiority of our method over existing systems.

pdf bib
Achieving Stronger Generation via Simple Contrastive Tuning
Zhimeng Wang | Pinzheng Wang | Juntao Li | Yibin Chen | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2024

Instruction tuning is widely used to unlock the abilities of Large Language Models (LLMs) in following human instructions, resulting in substantial performance improvements across various downstream tasks.Furthermore, contrastive decoding methods are employed to enhance instruction-tuned models. To further explore the potential of contrastive decoding, we introduce the Contrastive Tuning and Decoding (CTD) framework, which enhances model performance without requiring additional data or significant computational resources.When performing Contrastive Tuning, we optimize a correction model by targeting discrepancies between the original outputs and labels. During Contrastive Decoding, the correction model adjusts the logits of the SFT model using the same input to ensure better adherence to instructions.With the lightweight CTD framework, we refine the behavior of instruction-tuned models, improving their performance on the challenging SUPNATINST dataset with unfamiliar data distributions across various models and prompt formats.

pdf bib
AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Prediction
Shengkun Wang | Taoran Ji | Jianfeng He | Mariam ALMutairi | Dan Wang | Linhan Wang | Min Zhang | Chang-Tien Lu
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)

Stock volatility prediction is an important task in the financial industry. Recent multimodal methods have shown advanced results by combining text and audio information, such as earnings calls. However, these multimodal methods have faced two drawbacks. First, they often fail to yield reliable models and overfit the data due to their absorption of stochastic information from the stock market. Moreover, using multimodal models to predict stock volatility suffers from gender bias and lacks an efficient way to eliminate such bias. To address these aforementioned problems, we use adversarial training to generate perturbations that simulate the inherent stochasticity and bias, by creating areas resistant to random information around the input space to improve model robustness and fairness. Our comprehensive experiments on two real-world financial audio datasets reveal that this method exceeds the performance of current state-of-the-art solution. This confirms the value of adversarial training in reducing stochasticity and bias for stock volatility prediction tasks.

pdf bib
Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)
Kam-Fai Wong | Min Zhang | Ruifeng Xu | Jing Li | Zhongyu Wei | Lin Gui | Bin Liang | Runcong Zhao
Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)

pdf bib
Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm
Hexuan Deng | Xin Zhang | Meishan Zhang | Xuebo Liu | Min Zhang
Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)

In this paper, we conduct a holistic exploration of Universal Decompositional Semantic (UDS) parsing, aiming to provide a more efficient and effective solution for semantic parsing and to envision the development prospects after the emergence of large language models (LLMs). To achieve this, we first introduce a cascade model for UDS parsing that decomposes the complex task into semantically appropriate subtasks. Our approach outperforms prior models while significantly reducing inference time. Furthermore, to further exploit the hierarchical and automated annotation process of UDS, we explore the use of syntactic information and pseudo-labels, both of which enhance UDS parsing. Lastly, we investigate ChatGPT’s efficacy in handling the UDS task, highlighting its proficiency in attribute parsing but struggles in relation parsing, revealing that small parsing models still hold research significance. Our code is available at https://github.com/hexuandeng/HExp4UDS.

pdf bib
LLM-Assisted Data Augmentation for Chinese Dialogue-Level Dependency Parsing
Meishan Zhang | Gongyao Jiang | Shuang Liu | Jing Chen | Min Zhang
Computational Linguistics, Volume 50, Issue 3 - September 2024

Dialogue-level dependency parsing, despite its growing academic interest, often encounters underperformance issues due to resource shortages. A potential solution to this challenge is data augmentation. In recent years, large language models (LLMs) have demonstrated strong capabilities in generation, which can facilitate data augmentation greatly. In this study, we focus on Chinese dialogue-level dependency parsing, presenting three simple and effective strategies with LLM to augment the original training instances, namely word-level, syntax-level, and discourse-level augmentations, respectively. These strategies enable LLMs to either preserve or modify dependency structures, thereby assuring accuracy while increasing the diversity of instances at different levels. We conduct experiments on the benchmark dataset released by Jiang et al. (2023) to validate our approach. Results show that our method can greatly boost the parsing performance in various settings, particularly in dependencies among elementary discourse units. Lastly, we provide in-depth analysis to show the key points of our data augmentation strategies.

pdf bib
Pause-Aware Automatic Dubbing using LLM and Voice Cloning
Yuang Li | Jiaxin Guo | Min Zhang | Ma Miaomiao | Zhiqiang Rao | Weidong Zhang | Xianghui He | Daimeng Wei | Hao Yang
Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)

Automatic dubbing aims to translate the speech of a video into another language, ensuring the new speech naturally fits the original video. This paper details Huawei Translation Services Center’s (HW-TSC) submission for IWSLT 2024’s automatic dubbing task, under an unconstrained setting. Our system’s machine translation (MT) component utilizes a Transformer-based MT model and an LLM-based post-editor to produce translations of varying lengths. The text-to-speech (TTS) component employs a VITS-based TTS model and a voice cloning module to emulate the original speaker’s vocal timbre. For enhanced dubbing synchrony, we introduce a parsing-informed pause selector. Finally, we rerank multiple results based on lip-sync error distance (LSE-D) and character error rate (CER). Our system achieves LSE-D of 10.75 and 12.19 on subset1 and subset2 of DE-EN test sets respectively, superior to last year’s best system.

pdf bib
HW-TSC 2024 Submission for the Quality Estimation Shared Task
Weiqiao Shan | Ming Zhu | Yuang Li | Mengyao Piao | Xiaofeng Zhao | Chang Su | Min Zhang | Hao Yang | Yanfei Jiang
Proceedings of the Ninth Conference on Machine Translation

Quality estimation (QE) is a crucial technique for evaluating the quality of machine translations without the need for reference translations. This paper focuses on Huawei Translation Services Center’s (HW-TSC’s) submission to the sentence-level QE shared task, named LLMs-enhanced-CrossQE. Our system builds upon the CrossQE architecture from our submission from last year, which consists of a multilingual base model and a task-specific downstream layer. The model input is a concatenation of the source and the translated sentences. To enhance performance, we fine-tuned and ensembled multiple base models, including XLM-R, InfoXLM, RemBERT, and CometKiwi. Specifically, we employed two pseudo-data generation methods: 1) a diverse pseudo-data generation method based on the corruption-based data augmentation technique introduced last year, and 2) a pseudo-data generation method that simulates machine translation errors using large language models (LLMs). Our results demonstrate that the system achieves outstanding performance on sentence-level QE test sets.

pdf bib
HW-TSC’s Participation in the WMT 2024 QEAPE Task
Jiawei Yu | Xiaofeng Zhao | Min Zhang | Zhao Yanqing | Yuang Li | Su Chang | Xiaosong Qiao | Ma Miaomiao | Hao Yang
Proceedings of the Ninth Conference on Machine Translation

The paper presents the submission by HW-TSC in the WMT 2024 Quality-informed Automatic Post Editing (QEAPE) shared task for the English-Hindi (En-Hi) and English-Tamil (En-Ta) language pair. We use LLM for En-Hi and Transformer for EN-ta respectively. For LLM, we first continue pertrain the Llama3, and then use the real APE data to SFT the pre-trained LLM. As for the transformer in En-Ta, we first pre-train a Machine Translation (MT) model by utilizing MT data collected from the web. Then, we fine-tune the model by employing real APE data.We also use the data augmentation method to enhance our model. Specifically, we incorporate candidate translations obtained from an external Machine Translation (MT) system.Given that APE systems tend to exhibit a tendency of ‘over-correction’, we employ a sentence-level Quality Estimation (QE) system to select the final output, deciding between the original translation and the corresponding output generated by the APE model. Our experiments demonstrate that pre-trained MT models are effective when being fine-tuned with the APE corpus of a limited size, and the performance can be further improved with external MT augmentation. our approach improves the HTER by -15.99 points and -0.47 points on En-Hi and En-Ta, respectively.

pdf bib
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation
Zhengrui Ma | Qingkai Fang | Shaolei Zhang | Shoutao Guo | Yang Feng | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Simultaneous translation models play a crucial role in facilitating communication. However, existing research primarily focuses on text-to-text or speech-to-text models, necessitating additional cascade components to achieve speech-to-speech translation. These pipeline methods suffer from error propagation and accumulate delays in each cascade component, resulting in reduced synchronization between the speaker and listener. To overcome these challenges, we propose a novel non-autoregressive generation framework for simultaneous speech translation (NAST-S2x), which integrates speech-to-text and speech-to-speech tasks into a unified end-to-end framework.We develop a non-autoregressive decoder capable of concurrently generating multiple text or acoustic unit tokens upon receiving fixed-length speech chunks. The decoder can generate blank or repeated tokens and employ CTC decoding to dynamically adjust its latency. Experimental results show that NAST-S2x outperforms state-of-the-art models in both speech-to-text and speech-to-speech tasks. It achieves high-quality simultaneous interpretation within a delay of less than 3 seconds and provides a 28× decoding speedup in offline generation.

pdf bib
CopyNE: Better Contextual ASR by Copying Named Entities
Shilin Zhou | Zhenghua Li | Yu Hong | Min Zhang | Zhefeng Wang | Baoxing Huai
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

End-to-end automatic speech recognition (ASR) systems have made significant progress in general scenarios. However, it remains challenging to transcribe contextual named entities (NEs) in the contextual ASR scenario. Previous approaches have attempted to address this by utilizing the NE dictionary. These approaches treat entities as individual tokens and generate them token-by-token, which may result in incomplete transcriptions of entities. In this paper, we treat entities as indivisible wholes and introduce the idea of copying into ASR. We design a systematic mechanism called CopyNE, which can copy entities from the NE dictionary. By copying all tokens of an entity at once, we can reduce errors during entity transcription, ensuring the completeness of the entity. Experiments demonstrate that CopyNE consistently improves the accuracy of transcribing entities compared to previous approaches. Even when based on the strong Whisper, CopyNE still achieves notable improvements.

pdf bib
Temporal Knowledge Question Answering via Abstract Reasoning Induction
Ziyang Chen | Dongfang Li | Xiang Zhao | Baotian Hu | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this study, we address the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs). LLMs often struggle with this task, leading to the generation of inaccurate or misleading responses. This issue mainly arises from their limited ability to handle evolving factual knowledge and complex temporal logic. To overcome these limitations, we propose Abstract Reasoning Induction (ARI) framework, which divides temporal reasoning into two distinct phases: Knowledge agnostic and Knowledge-based. This framework offers factual knowledge support to LLMs while minimizing the incorporation of extraneous noisy data. Concurrently, informed by the principles of constructivism, ARI provides LLMs the capability to engage in proactive, self-directed learning from both correct and incorrect historical reasoning samples. By teaching LLMs to actively construct knowledge and methods, it can significantly boosting their temporal reasoning abilities. Our approach achieves significant improvements, with relative gains of 29.7% and 9.27% on two temporal QA datasets, underscoring its efficacy in advancing temporal reasoning in LLMs. The code can be found at https: //github.com/czy1999/ARI-QA.

pdf bib
TasTe: Teaching Large Language Models to Translate through Self-Reflection
Yutong Wang | Jiali Zeng | Xuebo Liu | Fandong Meng | Jie Zhou | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. Techniques like instruction tuning have effectively enhanced the proficiency of LLMs in the downstream task of machine translation. However, the existing approaches fail to yield satisfactory translation outputs that match the quality of supervised neural machine translation (NMT) systems. One plausible explanation for this discrepancy is that the straightforward prompts employed in these methodologies are unable to fully exploit the acquired instruction-following capabilities. To this end, we propose the TasTe framework, which stands for translating through self-reflection. The self-reflection process includes two stages of inference. In the first stage, LLMs are instructed to generate preliminary translations and conduct self-assessments on these translations simultaneously. In the second stage, LLMs are tasked to refine these preliminary translations according to the evaluation results. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods. Our work presents a promising approach to unleash the potential of LLMs and enhance their capabilities in MT. The codes and datasets are open-sourced at https://github.com/YutongWang1216/ReflectionLLMMT.

pdf bib
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
Qingkai Fang | Shaolei Zhang | Zhengrui Ma | Min Zhang | Yang Feng
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recently proposed two-pass direct speech-to-speech translation (S2ST) models decompose the task into speech-to-text translation (S2TT) and text-to-speech (TTS) within an end-to-end model, yielding promising results. However, the training of these models still relies on parallel speech data, which is extremely challenging to collect. In contrast, S2TT and TTS have accumulated a large amount of data and pretrained models, which have not been fully utilized in the development of S2ST models. Inspired by this, in this paper, we first introduce a composite S2ST model named ComSpeech, which can seamlessly integrate any pretrained S2TT and TTS models into a direct S2ST model. Furthermore, to eliminate the reliance on parallel speech data, we propose a novel training method ComSpeech-ZS that solely utilizes S2TT and TTS data. It aligns representations in the latent space through contrastive learning, enabling the speech synthesis capability learned from the TTS data to generalize to S2ST in a zero-shot manner. Experimental results on the CVSS dataset show that when the parallel speech data is available, ComSpeech surpasses previous two-pass models like UnitY and Translatotron 2 in both translation quality and decoding speed. When there is no parallel speech data, ComSpeech-ZS lags behind by only 0.7 ASR-BLEU and outperforms the cascaded models.

pdf bib
Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder
Jiaqi Wang | Zhenxi Song | Zhengyu Ma | Xipeng Qiu | Min Zhang | Zhiguo Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Reconstructing natural language from non-invasive electroencephalography (EEG) holds great promise as a language decoding technology for brain-computer interfaces (BCIs). However, EEG-based language decoding is still in its nascent stages, facing several technical issues such as: 1) Absence of a hybrid strategy that can effectively integrate cross-modality (between EEG and text) self-learning with intra-modality self-reconstruction of EEG features or textual sequences; 2) Under-utilization of large language models (LLMs) to enhance EEG-based language decoding. To address above issues, we propose the Contrastive EEG-Text Masked Autoencoder (CET-MAE), a novel model that orchestrates compound self-supervised learning across and within EEG and text through a dedicated multi-stream encoder. Furthermore, we develop a framework called E2T-PTR (EEG-to-Text decoding using Pretrained Transferable Representations), which leverages pre-trained modules alongside the EEG stream from CET-MAE and further enables an LLM (specifically BART) to decode text from EEG sequences. Comprehensive experiments conducted on the popular text-evoked EEG database, ZuCo, demonstrate the superiority of E2T-PTR, which outperforms the baseline framework in ROUGE-1 F1 and BLEU-4 scores by 8.34% and 32.21%, respectively. Our proposed pre-trained EEG-Text model shows the potential to improve downstream tasks involving EEG and text. This opens up promising avenues for its application in inner speech BCI paradigms, meriting further investigation.

pdf bib
Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment
Yunxin Li | Xinyu Chen | Baotian Hu | Haoyuan Shi | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alignment, especially aimed at challenging knowledge-based visual question answering (VQA). To this end, we present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Fine-grained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. Specifically, we design the VKA based on the interaction between a small language model and a visual encoder, training it on collected image-knowledge pairs to achieve visual knowledge acquisition and projection. FKA is employed to distill the fine-grained visual knowledge of an image and inject it into Large Language Models (LLMs). We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%). Ablation studies also verify the effectiveness of VKA and FKA, respectively.

pdf bib
Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation
Tengfei Yu | Xuebo Liu | Liang Ding | Kehai Chen | Dacheng Tao | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

End-to-end speech translation (ST) presents notable disambiguation challenges as it necessitates simultaneous cross-modal and cross-lingual transformations. While word sense disambiguation is an extensively investigated topic in textual machine translation, the exploration of disambiguation strategies for ST models remains limited. Addressing this gap, this paper introduces the concept of speech sense disambiguation (SSD), specifically emphasizing homophones - words pronounced identically but with different meanings. To facilitate this, we first create a comprehensive homophone dictionary and an annotated dataset rich with homophone information established based on speech-text alignment. Building on this unique dictionary, we introduce AmbigST, an innovative homophone-aware contrastive learning approach that integrates a homophone-aware masking strategy. Our experiments on different MuST-C and CoVoST ST benchmarks demonstrate that AmbigST sets new performance standards. Specifically, it achieves SOTA results on BLEU scores for English to German, Spanish, and French ST tasks, underlining its effectiveness in reducing speech sense ambiguity. Data, code and scripts are freely available at https://github.com/ytf-philp/AmbigST.

pdf bib
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Shaolei Zhang | Qingkai Fang | Shoutao Guo | Zhengrui Ma | Min Zhang | Yang Feng
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation between speech, Simul-S2ST requires a policy to control the model to generate corresponding target speech at the opportune moment within speech inputs, thereby posing a double challenge of translation and policy. In this paper, we propose StreamSpeech, a direct Simul-S2ST model that jointly learns translation and simultaneous policy in a unified framework of multi-task learning. Adhering to a multi-task learning approach, StreamSpeech can perform offline and simultaneous speech recognition, speech translation and speech synthesis via an “All-in-One” seamless model. Experiments on CVSS benchmark demonstrate that StreamSpeech achieves state-of-the-art performance in both offline S2ST and Simul-S2ST tasks. Besides, StreamSpeech is able to present high-quality intermediate results (i.e., ASR or translation results) during simultaneous translation process, offering a more comprehensive real-time communication experience.

pdf bib
Revisiting Demonstration Selection Strategies in In-Context Learning
Keqin Peng | Liang Ding | Yancheng Yuan | Xuebo Liu | Min Zhang | Yuanxin Ouyang | Dacheng Tao
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL), where a few examples are used to describe a task to the model. However, the performance of ICL varies significantly with the choice of demonstrations, and previous research usually focuses on the data aspect ignoring the model’s effect. In this work, we first revisit the factors contributing to this variance from the model aspect, and find that the demonstration choice is both data- and model-dependent. We further propose a conjecture that the performance of a demonstration positively correlates with its contribution to the model’s understanding of the test samples, and accordingly propose a data- and model-dependent demonstration selection method, TopK + ConE. Empirically, our method yields consistent improvements in both language understanding and generation tasks with different model scales. Further analyses confirm that, besides the generality and stability under different circumstances, our method provides a unified explanation for the effectiveness of previous methods. Code is publicly available at https://github.com/Romainpkq/revisit_demon_selection_in_ICL.

pdf bib
Multimodal Reasoning with Multimodal Knowledge Graph
Junlin Lee | Yequan Wang | Jing Li | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Multimodal reasoning with large language models (LLMs) often suffers from hallucinations and the presence of deficient or outdated knowledge within LLMs. Some approaches have sought to mitigate these issues by employing textual knowledge graphs, but their singular modality of knowledge limits comprehensive cross-modal understanding. In this paper, we propose the Multimodal Reasoning with Multimodal Knowledge Graph (MR-MKG) method, which leverages multimodal knowledge graphs (MMKGs) to learn rich and semantic knowledge across modalities, significantly enhancing the multimodal reasoning capabilities of LLMs. In particular, a relation graph attention network is utilized for encoding MMKGs and a cross-modal alignment module is designed for optimizing image-text alignment. A MMKG-grounded dataset is constructed to equip LLMs with initial expertise in multimodal reasoning through pretraining. Remarkably, MR-MKG achieves superior performance while training on only a small fraction of parameters, approximately 2.25% of the LLM’s parameter size. Experimental results on multimodal question answering and multimodal analogy reasoning tasks demonstrate that our MR-MKG method outperforms previous state-of-the-art models.

pdf bib
Don’t Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection
Min Zhang | Jianfeng He | Taoran Ji | Chang-Tien Lu
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The fairness and trustworthiness of Large Language Models (LLMs) are receiving increasing attention. Implicit hate speech, which employs indirect language to convey hateful intentions, occupies a significant portion of practice. However, the extent to which LLMs effectively address this issue remains insufficiently examined. This paper delves into the capability of LLMs to detect implicit hate speech and express confidence in their responses. Our evaluation meticulously considers various prompt patterns and mainstream uncertainty estimation methods. Our findings highlight that LLMs exhibit two extremes: (1) LLMs display excessive sensitivity towards groups or topics that may cause fairness issues, resulting in misclassifying benign statements as hate speech. (2) LLMs’ confidence scores for each method excessively concentrate on a fixed range, remaining unchanged regardless of the dataset’s complexity. Consequently, the calibration performance is heavily reliant on primary classification accuracy. These discoveries unveil new limitations of LLMs, underscoring the need for caution when optimizing models to ensure they do not veer towards extremes. This serves as a reminder to carefully consider sensitivity and confidence in the pursuit of model fairness.

pdf bib
Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?
Zhaochen Su | Juntao Li | Jun Zhang | Tong Zhu | Xiaoye Qu | Pan Zhou | Yan Bowen | Yu Cheng | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Temporal reasoning is fundamental for large language models (LLMs) to comprehend the world. Current temporal reasoning datasets are limited to questions about single or isolated events, falling short in mirroring the realistic temporal characteristics involving concurrent nature and intricate temporal interconnections. In this paper, we introduce CoTempQA, a comprehensive co-temporal Question Answering (QA) benchmark containing four co-temporal scenarios (Equal, Overlap, During, Mix) with 4,748 samples for evaluating the co-temporal comprehension and reasoning abilities of LLMs. Our extensive experiments reveal a significant gap between the performance of current LLMs and human-level reasoning on CoTempQA tasks. Even when enhanced with Chain of Thought (CoT) methodologies, models consistently struggle with our task. In our preliminary exploration, we discovered that mathematical reasoning plays a significant role in handling co-temporal events and proposed a strategy to boost LLMs’ co-temporal reasoning from a mathematical perspective. We hope that our CoTempQA datasets will encourage further advancements in improving the co-temporal reasoning capabilities of LLMs.

pdf bib
Context Consistency between Training and Inference in Simultaneous Machine Translation
Meizhi Zhong | Lemao Liu | Kehai Chen | Mingming Yang | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing source-side context.However, there is a counterintuitive phenomenon about the context usage between training and inference: *e.g.*, in wait-k inference, model consistently trained with wait-k is much worse than that model inconsistently trained with wait-k' (k'≠ k) in terms of translation quality. To this end, we first investigate the underlying reasons behind this phenomenon and uncover the following two factors: 1) the limited correlation between translation quality and training loss; 2) exposure bias between training and inference. Based on both reasons, we then propose an effective training approach called context consistency training accordingly, which encourages consistent context usage between training and inference by optimizing translation quality and latency as bi-objectives and exposing the predictions to the model during the training. The experiments on three language pairs demonstrate that our SiMT system encouraging context consistency outperforms existing SiMT systems with context inconsistency for the first time.

pdf bib
DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
Andong Chen | Lianzhang Lou | Kehai Chen | Xuefeng Bai | Yang Xiang | Muyun Yang | Tiejun Zhao | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine transla004 tion. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection methods lack effective feedback information, limiting the translation performance. To address this, we introduce a DUAL-REFLECT framework, leveraging the dual learning of translation tasks to provide effective feedback, thereby enhancing the models’ self-reflective abilities and improving translation performance. The application of this method across various translation tasks has proven its effectiveness in improving translation accuracy and eliminating ambiguities, especially in translation tasks with low-resource language pairs.

pdf bib
On the Hallucination in Simultaneous Machine Translation
Meizhi Zhong | Kehai Chen | Zhengshan Xue | Lemao Liu | Mingming Yang | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

It is widely known that hallucination is a critical issue in Simultaneous Machine Translation (SiMT) due to the absence of source-side information. While many efforts have been made to enhance performance for SiMT, few of them attempt to understand and analyze hallucination in SiMT.Therefore, we conduct a comprehensive analysis of hallucination in SiMT from two perspectives: understanding the distribution of hallucination words and the target-side context usage of them.Intensive experiments demonstrate some valuable findings and particularly show that it is possible to alleviate hallucination by decreasing the over usage of target-side information for SiMT.

pdf bib
XNLP: An Interactive Demonstration System for Universal Structured NLP
Hao Fei | Meishan Zhang | Min Zhang | Tat-Seng Chua
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)

Structured Natural Language Processing (XNLP) is an important subset of NLP that entails understanding the underlying semantic or syntactic structure of texts, which serves as a foundational component for many downstream applications. Despite certain recent efforts to explore universal solutions for specific categories of XNLP tasks, a comprehensive and effective approach for unifying all XNLP tasks long remains underdeveloped. Meanwhile, while XNLP demonstration systems are vital for researchers exploring various XNLP tasks, existing platforms can be limited to, e.g., supporting few XNLP tasks, lacking interactivity and universalness. To this end, we propose an advanced XNLP demonstration system, where we leverage LLM to achieve universal XNLP, with one model for all with high generalizability. Overall, our system advances in multiple aspects, including universal XNLP modeling, high performance, interpretability, scalability, and interactivity, offering a unified platform for exploring diverse XNLP tasks in the community.

pdf bib
3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
Xinyu Ma | Xuebo Liu | Derek F. Wong | Jun Rao | Bei Li | Liang Ding | Lidia S. Chao | Dacheng Tao | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Multimodal machine translation (MMT) is a challenging task that seeks to improve translation quality by incorporating visual information. However, recent studies have indicated that the visual information provided by existing MMT datasets is insufficient, causing models to disregard it and overestimate their capabilities. This issue presents a significant obstacle to the development of MMT research. This paper presents a novel solution to this issue by introducing 3AM, an ambiguity-aware MMT dataset comprising 26,000 parallel sentence pairs in English and Chinese, each with corresponding images. Our dataset is specifically designed to include more ambiguity and a greater variety of both captions and images than other MMT datasets. We utilize a word sense disambiguation model to select ambiguous data from vision-and-language datasets, resulting in a more challenging dataset. We further benchmark several state-of-the-art MMT models on our proposed dataset. Experimental results show that MMT models trained on our dataset exhibit a greater ability to exploit visual information than those trained on other MMT datasets. Our work provides a valuable resource for researchers in the field of multimodal learning and encourages further exploration in this area. The data, code and scripts are freely available at https://github.com/MaxyLee/3AM.

pdf bib
A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation
Yunxin Li | Baotian Hu | Wenhan Luo | Lin Ma | Yuxin Ding | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

In this paper, we propose a new setting for generating product descriptions from images, augmented by marketing keywords. It leverages the combined power of visual and textual information to create descriptions that are more tailored to the unique features of products. For this setting, previous methods utilize visual and textual encoders to encode the image and keywords and employ a language model-based decoder to generate the product description. However, the generated description is often inaccurate and generic since same-category products have similar copy-writings, and optimizing the overall framework on large-scale samples makes models concentrate on common words yet ignore the product features. To alleviate the issue, we present a simple and effective Multimodal In-Context Tuning approach, named ModICT, which introduces a similar product sample as the reference and utilizes the in-context learning capability of language models to produce the description. During training, we keep the visual encoder and language model frozen, focusing on optimizing the modules responsible for creating multimodal in-context references and dynamic prompts. This approach preserves the language generation prowess of large language models (LLMs), facilitating a substantial increase in description diversity. To assess the effectiveness of ModICT across various language model scales and types, we collect data from three distinct product categories within the E-commerce domain. Extensive experiments demonstrate that ModICT significantly improves the accuracy (by up to 3.3% on Rouge-L) and diversity (by up to 9.4% on D-5) of generated results compared to conventional methods. Our findings underscore the potential of ModICT as a valuable tool for enhancing the automatic generation of product descriptions in a wide range of applications. Data and code are at https://github.com/HITsz-TMG/Multimodal-In-Context-Tuning

pdf bib
CB-Whisper: Contextual Biasing Whisper Using Open-Vocabulary Keyword-Spotting
Yuang Li | Yinglu Li | Min Zhang | Chang Su | Jiawei Yu | Mengyao Piao | Xiaosong Qiao | Miaomiao Ma | Yanqing Zhao | Hao Yang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations and terminologies that are not frequently encountered in the training data. This paper presents Contextual Biasing Whisper (CB-Whisper), a novel ASR system based on OpenAI’s Whisper model that can recognize user-defined name entities by performing open-vocabulary keyword-spotting (KWS) before the decoder. The KWS module leverages text-to-speech (TTS) techniques and a convolutional neural network (CNN) classifier to match the features between the entities and the utterances. To integrate the recognized entities into the Whipser decoder and avoid hallucinations, we carefully crafted multiple prompts with spoken form hints. Experiments show that the KWS module based on Whisper encoder’s features can recognize unseen user-defined keywords effectively. More importantly, the proposed CB-Whisper substantially improves the mixed-error-rate (MER) and entity recall compared to the original Whisper model on three internal datasets and two publicly available datasets including Aishell and ACL datasets that cover English-only, Chinese-only, and code-switching scenarios.

pdf bib
Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training
Longhui Zhang | Dingkun Long | Meishan Zhang | Yanzhao Zhang | Pengjun Xie | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Chinese sequence labeling tasks are sensitive to word boundaries. Although pretrained language models (PLM) have achieved considerable success in these tasks, current PLMs rarely consider boundary information explicitly. An exception to this is BABERT, which incorporates unsupervised statistical boundary information into Chinese BERT’s pre-training objectives. Building upon this approach, we input supervised high-quality boundary information to enhance BABERT’s learning, developing a semi-supervised boundary-aware PLM. To assess PLMs’ ability to encode boundaries, we introduce a novel “Boundary Information Metric” that is both simple and effective. This metric allows comparison of different PLMs without task-specific fine-tuning. Experimental results on Chinese sequence labeling datasets demonstrate that the improved BABERT version outperforms the vanilla version, not only in these tasks but also in broader Chinese natural language understanding tasks. Additionally, our proposed metric offers a convenient and accurate means of evaluating PLMs’ boundary awareness.

pdf bib
Exploring and Mitigating Shortcut Learning for Generative Large Language Models
Zechen Sun | Yisheng Xiao | Juntao Li | Yixin Ji | Wenliang Chen | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Recent generative large language models (LLMs) have exhibited incredible instruction-following capabilities while keeping strong task completion ability, even without task-specific fine-tuning. Some works attribute this to the bonus of the new scaling law, in which the continuous improvement of model capacity yields emergent capabilities, e.g., reasoning and universal generalization. However, we point out that recent LLMs still show shortcut learning behavior, where the models tend to exploit spurious correlations between non-robust features and labels for prediction, which might lead to overestimating model capabilities. LLMs memorize more complex spurious correlations (i.e., task feature label) compared with that learned from previous pre-training and task-specific fine-tuning paradigm (i.e., feature label). Based on our findings, we propose FSLI, a framework for encouraging LLMs to Forget Spurious correlations and Learn from In-context information. Experiments on three tasks show that FSFI can effectively mitigate shortcut learning. Besides, we argue not to overestimate the capabilities of LLMs and conduct evaluations in more challenging and complete test scenarios.

pdf bib
Generative Multimodal Entity Linking
Senbao Shi | Zhenran Xu | Baotian Hu | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base. Existing MEL methods mainly focus on designing complex multimodal interaction mechanisms and require fine-tuning all model parameters, which can be prohibitively costly and difficult to scale in the era of Large Language Models (LLMs). In this work, we propose GEMEL, a Generative Multimodal Entity Linking framework based on LLMs, which directly generates target entity names. We keep the vision and language model frozen and only train a feature mapper to enable cross-modality interactions. To adapt LLMs to the MEL task, we leverage the in-context learning capability of LLMs by retrieving multimodal instances as demonstrations. Extensive experiments show that, with only ∼0.3% of the model parameters fine-tuned, GEMEL achieves state-of-the-art results on two well-established MEL datasets (7.7% accuracy gains on WikiDiverse and 8.8% accuracy gains on WikiMEL). The performance gain stems from mitigating the popularity bias of LLM predictions and disambiguating less common entities effectively. Further analysis verifies the generality and scalability of GEMEL. Our framework is compatible with any off-the-shelf language model, paving the way towards an efficient and general solution for utilizing LLMs in the MEL task. Our code is available at https://github.com/HITsz-TMG/GEMEL.

pdf bib
Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling
Chenhui Dou | Chen Gong | Zhenghua Li | Zhefeng Wang | Baoxing Huai | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Nowadays, character-based sequence labeling becomes the mainstream Chinese named entity recognition (CNER) approach, instead of word-based methods, since the latter degrades performance due to propagation of word segmentation (WS) errors. To make use of WS information, previous studies usually learn CNER and WS simultaneously with multi-task learning (MTL) framework, or treat WS information as extra guide features for CNER model, in which the utilization of WS information is indirect and shallow. In light of the complementary information inside multi-grained words, and the close connection between named entities and part-of-speech (POS) tags, this work proposes a tree parsing approach for joint modeling CNER, multi-grained word segmentation (MWS) and POS tagging tasks simultaneously. Specifically, we first propose a unified tree representation for MWS, POS tagging, and CNER.Then, we automatically construct the MWS-POS-NER data based on the unified tree representation for model training. Finally, we present a two-stage joint tree parsing framework. Experimental results on OntoNotes4 and OntoNotes5 show that our proposed approach of jointly modeling CNER with MWS and POS tagging achieves better or comparable performance with latest methods.

pdf bib
Multimodal Cross-lingual Phrase Retrieval
Chuanqi Dong | Wenjie Zhou | Xiangyu Duan | Yuqi Zhang | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Cross-lingual phrase retrieval aims to retrieve parallel phrases among languages. Current approaches only deals with textual modality. There lacks multimodal data resources and explorations for multimodal cross-lingual phrase retrieval (MXPR). In this paper, we create the first MXPR data resource and propose a novel approach for MXPR to explore the effectiveness of multi-modality. The MXPR data resource is built by marrying the benchmark dataset for textual cross-lingual phrase retrieval with Wikimedia Commons, which is a media store containing tremendous texts and related images. In the built resource, the phrase pairs of the textual benchmark dataset are equipped with their related images. Based on this novel data resource, we introduce a strategy to bridge the gap between different modalities by multimodal relation generation with a large multimodal pre-trained model and consistency training. Experiments on benchmarked dataset covering eight language pairs show that our MXPR approach, which deals with multimodal phrases, performs significantly better than pure textual cross-lingual phrase retrieval.

pdf bib
Submodular-based In-context Example Selection for LLMs-based Machine Translation
Baijun Ji | Xiangyu Duan | Zhenyu Qiu | Tong Zhang | Junhui Li | Hao Yang | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Large Language Models (LLMs) have demonstrated impressive performances across various NLP tasks with just a few prompts via in-context learning. Previous studies have emphasized the pivotal role of well-chosen examples in in-context learning, as opposed to randomly selected instances that exhibits unstable results.A successful example selection scheme depends on multiple factors, while in the context of LLMs-based machine translation, the common selection algorithms only consider the single factor, i.e., the similarity between the example source sentence and the input sentence.In this paper, we introduce a novel approach to use multiple translational factors for in-context example selection by using monotone submodular function maximization.The factors include surface/semantic similarity between examples and inputs on both source and target sides, as well as the diversity within examples.Importantly, our framework mathematically guarantees the coordination between these factors, which are different and challenging to reconcile.Additionally, our research uncovers a previously unexamined dimension: unlike other NLP tasks, the translation part of an example is also crucial, a facet disregarded in prior studies.Experiments conducted on BLOOMZ-7.1B and LLAMA2-13B, demonstrate that our approach significantly outperforms random selection and robust single-factor baselines across various machine translation tasks.

pdf bib
Towards More Realistic Chinese Spell Checking with New Benchmark and Specialized Expert Model
Yue Wang | Zilong Zheng | Juntao Li | Zhihui Liu | Jinxiong Chang | Qishen Zhang | Zhongyi Liu | Guannan Zhang | Min Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Large Language Models (LLMs) hold considerable promise for artificial general intelligence, given their intrinsic abilities to accomplish a wide range of open-domain tasks either independently or in tandem with specialized expert models. However, despite these capabilities, the performance of LLMs has yet to be comprehensively evaluated in realistic scenarios. To this end, in this work, we introduce a novel task, the Realistic Chinese Spell Checking (RCSC), to evaluate the effectiveness of existing methods comprehensively. In contrast to existing works that solely address Chinese character misspellings or pinyin conversions, our task aims to convert the realistic Chinese text into the corresponding correct text. The realistic Chinese text may potentially contain both Chinese misspellings and pinyin conversions. We first present the Realistic Chinese Spell Checking Benchmark (RCSCB), which consists of two subsets and contains a total of 581,657 samples. Then, we benchmark the performance of various baselines and find that all the existing methods, including instruction-based LLMs, achieve unsatisfactory results on RCSCB. To further improve the performance on RCSCB, we propose Pinyin-Enhanced Spell Checker (PESC), which is specifically designed to address pinyin-related misspellings. Experimental results demonstrate that PESC can achieve state-of-the-art performance on RCSCB. Despite the progress made, the current state-of-the-art performance is still far from satisfactory. We expect further progress on this crucial and challenging task.

pdf bib
HW-TSC 2024 Submission for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR)
Mengyao Piao | Su Chang | Yuang Li | Xiaosong Qiao | Xiaofeng Zhao | Yinglu Li | Min Zhang | Hao Yang
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

The degree of semantic relatedness of two units of language has long been considered fundamental to understanding meaning. In this paper, we present the system of Huawei Translation Services Center (HW-TSC) for Task 1 of SemEval 2024, which aims to automatically measure the semantic relatedness of sentence pairs in African and Asian languages. The task dataset for this task covers about 14 different languages, These languages originate from five distinct language families and are predominantly spoken in Africa and Asia. For this shared task, we describe our proposed solutions, including ideas and the implementation steps of the task, as well as the outcomes of each experiment on the development dataset. To enhance the performance, we leverage these experimental outcomes and construct an ensemble one. Our results demonstrate that our system achieves impressive performance on test datasets in unsupervised track B and ranked first place for the Punjabi language pair.

pdf bib
HW-TSC at SemEval-2024 Task 9: Exploring Prompt Engineering Strategies for Brain Teaser Puzzles Through LLMs
Yinglu Li | Zhao Yanqing | Min Zhang | Yadong Deng | Aiju Geng | Xiaoqin Liu | Mengxin Ren | Yuang Li | Su Chang | Xiaofeng Zhao
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

Large Language Models (LLMs) have demonstrated impressive performance on many Natural Language Processing (NLP) tasks. However, their ability to solve more creative, lateral thinking puzzles remains relatively unexplored. In this work, we develop methods to enhance the lateral thinking and puzzle-solving capabilities of LLMs. We curate a dataset of word-type and sentence-type brain teasers requiring creative problem-solving abilities beyond commonsense reasoning. We first evaluate the zero-shot performance of models like GPT-3.5 and GPT-4 on this dataset. To improve their puzzle-solving skills, we employ prompting techniques like providing reasoning clues and chaining multiple examples to demonstrate the desired thinking process. We also fine-tune the state-of-the-art Mixtral 7x8b LLM on ourdataset. Our methods enable the models to achieve strong results, securing 2nd and 3rd places in the brain teaser task. Our work highlights the potential of LLMs in acquiring complex reasoning abilities with the appropriate training. The efficacy of our approaches opens up new research avenues into advancing lateral thinking and creative problem-solving with AI systems.

pdf bib
HW-TSC at SemEval-2024 Task 5: Self-Eval? A Confident LLM System for Auto Prediction and Evaluation for the Legal Argument Reasoning Task
Xiaofeng Zhao | Xiaosong Qiao | Kaiwen Ou | Min Zhang | Su Chang | Mengyao Piao | Yuang Li | Yinglu Li | Ming Zhu | Yilun Liu
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

In this article, we present an effective system for semeval-2024 task 5. The task involves assessing the feasibility of a given solution in civil litigation cases based on relevant legal provisions, issues, solutions, and analysis. This task demands a high level of proficiency in U.S. law and natural language reasoning. In this task, we designed a self-eval LLM system that simultaneously performs reasoning and self-assessment tasks. We created a confidence interval and a prompt instructing the LLM to output the answer to a question along with its confidence level. We designed a series of experiments to prove the effectiveness of the self-eval mechanism. In order to avoid the randomness of the results, the final result is obtained by voting on three results generated by the GPT-4. Our submission was conducted under zero-resource setting, and we achieved first place in the task with an F1-score of 0.8231 and an accuracy of 0.8673.

2023

pdf bib
HW-TSC at SemEval-2023 Task 7: Exploring the Natural Language Inference Capabilities of ChatGPT and Pre-trained Language Model for Clinical Trial
Xiaofeng Zhao | Min Zhang | Miaomiao Ma | Chang Su | Yilun Liu | Minghan Wang | Xiaosong Qiao | Jiaxin Guo | Yinglu Li | Wenbing Ma
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

In this paper, we describe the multi strategy system for SemEval-2022 Task 7, This task aims to determine whether a given statement is supported by one or two Clinical Trial reports, and to identify evidence that supports the statement. This is a task that requires high natural language inference capabilities. In Subtask 1, we compare our strategy based on prompt learning and ChatGPT with a baseline constructed using BERT in zero-shot setting, and validate the effectiveness of our strategy. In Subtask 2, we fine-tune DeBERTaV3 for classification without relying on the results from Subtask 1, and we observe that early stopping can effectively prevent model overfitting, which performs well in Subtask 2. In addition, we did not use any ensemble strategies. Ultimately, we achieved the 10th place in Subtask 1 and the 2nd place in Subtask 2.

pdf bib
Open-ended Long Text Generation via Masked Language Modeling
Xiaobo Liang | Zecheng Tang | Juntao Li | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Pre-trained autoregressive (AR) language models such as BART and GPTs have dominated OPen-ended Long Text Generation (Open-LTG).However, the AR nature will decrease the inference efficiency along with the increase of generation length, which hinder their application in Open-LTG.To improve inference efficiency, we alternatively explore the potential of the pre-trained masked language models (MLMs) along with a representative iterative non-autoregressive (NAR) decoding strategy for Open-LTG.Our preliminary study shows that pre-trained MLMs can merely generate short text and will collapse for long text modeling. To enhance the long text generation capability of MLMs, we introduce two simple yet effective strategies for the iterative NAR model: dynamic sliding window attention (DSWA) and linear temperature decay (LTD). It can alleviate long-distance collapse problems and achieve longer text generation with a flexible trade-off between performance and inference speedup. Experiments on the storytelling and multi-paragraph opinionated article writing tasks show that pre-trained MLMs can achieve more than 3 × 13 × speedup with better performance than strong AR models.

pdf bib
Test-time Adaptation for Machine Translation Evaluation by Uncertainty Minimization
Runzhe Zhan | Xuebo Liu | Derek F. Wong | Cuilian Zhang | Lidia S. Chao | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The neural metrics recently received considerable attention from the research community in the automatic evaluation of machine translation. Unlike text-based metrics that have interpretable and consistent evaluation mechanisms for various data sources, the reliability of neural metrics in assessing out-of-distribution data remains a concern due to the disparity between training data and real-world data. This paper aims to address the inference bias of neural metrics through uncertainty minimization during test time, without requiring additional data. Our proposed method comprises three steps: uncertainty estimation, test-time adaptation, and inference. Specifically, the model employs the prediction uncertainty of the current data as a signal to update a small fraction of parameters during test time and subsequently refine the prediction through optimization. To validate our approach, we apply the proposed method to three representative models and conduct experiments on the WMT21 benchmarks. The results obtained from both in-domain and out-of-distribution evaluations consistently demonstrate improvements in correlation performance across different models. Furthermore, we provide evidence that the proposed method effectively reduces model uncertainty. The code is publicly available at https://github.com/NLP2CT/TaU.

pdf bib
kNN-TL: k-Nearest-Neighbor Transfer Learning for Low-Resource Neural Machine Translation
Shudong Liu | Xuebo Liu | Derek F. Wong | Zhaocong Li | Wenxiang Jiao | Lidia S. Chao | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Transfer learning has been shown to be an effective technique for enhancing the performance of low-resource neural machine translation (NMT). This is typically achieved through either fine-tuning a child model with a pre-trained parent model, or by utilizing the out- put of the parent model during the training of the child model. However, these methods do not make use of the parent knowledge during the child inference, which may limit the translation performance. In this paper, we propose a k-Nearest-Neighbor Transfer Learning (kNN-TL) approach for low-resource NMT, which leverages the parent knowledge throughout the entire developing process of the child model. Our approach includes a parent-child representation alignment method, which ensures consistency in the output representations between the two models, and a child-aware datastore construction method that improves inference efficiency by selectively distilling the parent datastore based on relevance to the child model. Experimental results on four low-resource translation tasks show that kNN-TL outperforms strong baselines. Extensive analyses further demonstrate the effectiveness of our approach. Code and scripts are freely available at https://github.com/NLP2CT/kNN-TL.

pdf bib
Improving Gradient Trade-offs between Tasks in Multi-task Text Classification
Heyan Chai | Jinhao Cui | Ye Wang | Min Zhang | Binxing Fang | Qing Liao
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Multi-task learning (MTL) has emerged as a promising approach for sharing inductive bias across multiple tasks to enable more efficient learning in text classification. However, training all tasks simultaneously often yields degraded performance of each task than learning them independently, since different tasks might conflict with each other. Existing MTL methods for alleviating this issue is to leverage heuristics or gradient-based algorithm to achieve an arbitrary Pareto optimal trade-off among different tasks. In this paper, we present a novel gradient trade-off approach to mitigate the task conflict problem, dubbed GetMTL, which can achieve a specific trade-off among different tasks nearby the main objective of multi-task text classification (MTC), so as to improve the performance of each task simultaneously. The results of extensive experiments on two benchmark datasets back up our theoretical analysis and validate the superiority of our proposed GetMTL.

pdf bib
Dynamic and Efficient Inference for Text Generation via BERT Family
Xiaobo Liang | Juntao Li | Lijun Wu | Ziqiang Cao | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Despite the excellent performance of Pre-trained Language Models on many text generation tasks, they suffer from inefficient inference on computation and memory due to their large-scale parameters and the universal autoregressive decoding paradigm. In this work, we propose a novel fine-tuning method DEER, which can make a single pre-trained model support Dynamic and Efficient infERence and achieve an adaptive trade-off between model performance and latency. In particular, our critical insight is to jointly utilize the non-autoregressive (NAR) generation and dynamic parameter pruning techniques, which can flexibly control the decoding iteration steps and model sizes according to memory and latency limitations. Besides, we also explore the effectiveness of the pre-trained MLMs (i.e., the BERT family) for text generation tasks since their bidirectional attention nature is more suitable for the NAR training objective. Extensive experiments on both monolingual and multilingual pre-trained MLMs demonstrate the effectiveness of our proposed DEER method by consistently achieving (1) higher BLEU scores than the strong autoregressive Transformer model on three neural machine translation tasks with 3 12 times speedup, (2) competitive performance (but with much faster inference speed) compared with the BART model on four GLGE benchmark tasks. Our code will be publicly available at GitHub https://github.com/dropreg/DEER.

pdf bib
Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation
Zhiwei Cao | Baosong Yang | Huan Lin | Suhang Wu | Xiangpeng Wei | Dayiheng Liu | Jun Xie | Min Zhang | Jinsong Su
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

k-Nearest neighbor machine translation (kNN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains. By using an upstream NMT model to traverse the downstream training corpus, it is equipped with a datastore containing vectorized key-value pairs, which are retrieved during inference to benefit translation.However, there often exists a significant gap between upstream and downstream domains, which hurts the datastore retrieval and the final translation quality.To deal with this issue, we propose a novel approach to boost the datastore retrieval of kNN-MT by reconstructing the original datastore.Concretely, we design a reviser to revise the key representations, making them better fit for the downstream domain. The reviser is trained using the collected semantically-related key-queries pairs, and optimized by two proposed losses: one is the key-queries semantic distance ensuring each revised key representation is semantically related to its corresponding queries, and the other is an L2-norm loss encouraging revised key representations to effectively retain the knowledge learned by the upstream NMT model. Extensive experiments on domain adaptation tasks demonstrate that our method can effectively boost the datastore retrieval and translation quality of kNN-MT.Our code is available at https://github.com/DeepLearnXMU/Revised-knn-mt.

pdf bib
Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination
Hao Fei | Qian Liu | Meishan Zhang | Min Zhang | Tat-Seng Chua
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs. First, we represent the input images and texts with the visual and language scene graphs (SG), where such fine-grained vision-language features ensure a holistic understanding of the semantics. To enable pure-text input during inference, we devise a visual scene hallucination mechanism that dynamically generates pseudo visual SG from the given textual SG. Several SG-pivoting based learning objectives are introduced for unsupervised translation training. On the benchmark Multi30K data, our SG-based method outperforms the best-performing baseline by significant BLEU scores on the task and setup, helping yield translations with better completeness, relevance and fluency without relying on paired images. Further in-depth analyses reveal how our model advances in the task setting.

pdf bib
TemplateGEC: Improving Grammatical Error Correction with Detection Template
Yinghao Li | Xuebo Liu | Shuo Wang | Peiyuan Gong | Derek F. Wong | Yang Gao | Heyan Huang | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Grammatical error correction (GEC) can be divided into sequence-to-edit (Seq2Edit) and sequence-to-sequence (Seq2Seq) frameworks, both of which have their pros and cons. To utilize the strengths and make up for the shortcomings of these frameworks, this paper proposes a novel method, TemplateGEC, which capitalizes on the capabilities of both Seq2Edit and Seq2Seq frameworks in error detection and correction respectively. TemplateGEC utilizes the detection labels from a Seq2Edit model, to construct the template as the input. A Seq2Seq model is employed to enforce consistency between the predictions of different templates by utilizing consistency learning. Experimental results on the Chinese NLPCC18, English BEA19 and CoNLL14 benchmarks show the effectiveness and robustness of TemplateGEC.Further analysis reveals the potential of our method in performing human-in-the-loop GEC. Source code and scripts are available at https://github.com/li-aolong/TemplateGEC.

pdf bib
Generating Visual Spatial Description via Holistic 3D Scene Understanding
Yu Zhao | Hao Fei | Wei Ji | Jianguo Wei | Meishan Zhang | Min Zhang | Tat-Seng Chua
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical vision features, thus inevitably falling prey to the problem of skewed spatial understanding of target objects. In this work, we investigate the incorporation of 3D scene features for VSD. With an external 3D scene extractor, we obtain the 3D objects and scene features for input images, based on which we construct a target object-centered 3D spatial scene graph (Go3D-S2G), such that we model the spatial semantics of target objects within the holistic 3D scenes. Besides, we propose a scene subgraph selecting mechanism, sampling topologically-diverse subgraphs from Go3D-S2G, where the diverse local structure features are navigated to yield spatially-diversified text generation. Experimental results on two VSD datasets demonstrate that our framework outperforms the baselines significantly, especially improving on the cases with complex visual spatial relations. Meanwhile, our method can produce more spatially-diversified generation.

pdf bib
Revisiting Token Dropping Strategy in Efficient BERT Pretraining
Qihuang Zhong | Liang Ding | Juhua Liu | Xuebo Liu | Min Zhang | Bo Du | Dacheng Tao
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training time without degrading much performance on downstream tasks. However, we empirically find that token dropping is prone to a semantic loss problem and falls short in handling semantic-intense tasks. Motivated by this, we propose a simple yet effective semantic-consistent learning method (ScTD) to improve the token dropping. ScTD aims to encourage the model to learn how to preserve the semantic information in the representation space. Extensive experiments on 12 tasks show that, with the help of our ScTD, token dropping can achieve consistent and significant performance gains across all task types and model sizes. More encouragingly, ScTD saves up to 57% of pretraining time and brings up to +1.56% average improvement over the vanilla token dropping.

pdf bib
A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues
Yunxin Li | Baotian Hu | Chen Xinyu | Yuxin Ding | Lin Ma | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Conditional inference on joint textual and visual clues is a multi-modal reasoning task that textual clues provide prior permutation or external knowledge, which are complementary with visual content and pivotal to deducing the correct option. Previous methods utilizing pretrained vision-language models (VLMs) have achieved impressive performances, yet they show a lack of multimodal context reasoning capability, especially for text-modal information. To address this issue, we propose a Multi-modal Context Reasoning approach, named ModCR. Compared to VLMs performing reasoning via cross modal semantic alignment, it regards the given textual abstract semantic and objective image information as the pre-context information and embeds them into the language model to perform context reasoning. Different from recent vision-aided language models used in natural language processing, ModCR incorporates the multi-view semantic alignment information between language and vision by introducing the learnable alignment prefix between image and text in the pretrained language model. This makes the language model well-suitable for such multi-modal reasoning scenario on joint textual and visual clues. We conduct extensive experiments on two corresponding data sets and experimental results show significantly improved performance (exact gain by 4.8% on PMR test set) compared to previous strong baselines.

pdf bib
Revisiting Commonsense Reasoning in Machine Translation: Training, Evaluation and Challenge
Xuebo Liu | Yutong Wang | Derek F. Wong | Runzhe Zhan | Liangxuan Yu | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The ability of commonsense reasoning (CR) decides whether a neural machine translation (NMT) model can move beyond pattern recognition. Despite the rapid advancement of NMT and the use of pretraining to enhance NMT models, research on CR in NMT is still in its infancy, leaving much to be explored in terms of effectively training NMT models with high CR abilities and devising accurate automatic evaluation metrics. This paper presents a comprehensive study aimed at expanding the understanding of CR in NMT.For the training, we confirm the effectiveness of incorporating pretrained knowledge into NMT models and subsequently utilizing these models as robust testbeds for investigating CR in NMT. For the evaluation, we propose a novel entity-aware evaluation method that takes into account both the NMT candidate and important entities in the candidate, which is more aligned with human judgement. Based on the strong testbed and evaluation methods, we identify challenges in training NMT models with high CR abilities and suggest directions for further unlabeled data utilization and model design. We hope that our methods and findings will contribute to advancing the research of CR in NMT. Source data, code and scripts are freely available at https://github.com/YutongWang1216/CR-NMT.

pdf bib
A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text
Yunxin Li | Baotian Hu | Yuxin Ding | Lin Ma | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text. However, their performance drops drastically when confronted with linguistically complex texts that they struggle to comprehend. Inspired by the Divide-and-Conquer algorithm and dual-process theory, in this paper, we regard linguistically complex texts as compound proposition texts composed of multiple simple proposition sentences and propose an end-to-end Neural Divide-and-Conquer Reasoning framework, dubbed NDCR. It contains three main components: 1) Divide: a proposition generator divides the compound proposition text into simple proposition sentences and produces their corresponding representations, 2) Conquer: a pretrained VLMs-based visual-linguistic interactor achieves the interaction between decomposed proposition sentences and images, 3) Combine: a neural-symbolic reasoner combines the above reasoning states to obtain the final solution via a neural logic reasoning approach. According to the dual-process theory, the visual-linguistic interactor and neural-symbolic reasoner could be regarded as analogical reasoning System 1 and logical reasoning System 2. We conduct extensive experiments on a challenging image retrieval from contextual descriptions data set. Experimental results and analyses indicate NDCR significantly improves performance in the complex image-text reasoning problem.

pdf bib
The HW-TSC’s Speech-to-Speech Translation System for IWSLT 2023
Minghan Wang | Yinglu Li | Jiaxin Guo | Zongyao Li | Hengchao Shang | Daimeng Wei | Min Zhang | Shimin Tao | Hao Yang
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)

This paper describes our work on the IWSLT2023 Speech-to-Speech task. Our proposed cascaded system consists of an ensemble of Conformer and S2T-Transformer-based ASR models, a Transformer-based MT model, and a Diffusion-based TTS model. Our primary focus in this competition was to investigate the modeling ability of the Diffusion model for TTS tasks in high-resource scenarios and the role of TTS in the overall S2S task. To this end, we proposed DTS, an end-to-end diffusion-based TTS model that takes raw text as input and generates waveform by iteratively denoising on pure Gaussian noise. Compared to previous TTS models, the speech generated by DTS is more natural and performs better in code-switching scenarios. As the training process is end-to-end, it is relatively straightforward. Our experiments demonstrate that DTS outperforms other TTS models on the GigaS2S benchmark, and also brings positive gains for the entire S2S system.

pdf bib
TransGEC: Improving Grammatical Error Correction with Translationese
Tao Fang | Xuebo Liu | Derek F. Wong | Runzhe Zhan | Liang Ding | Lidia S. Chao | Dacheng Tao | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Data augmentation is an effective way to improve model performance of grammatical error correction (GEC). This paper identifies a critical side-effect of GEC data augmentation, which is due to the style discrepancy between the data used in GEC tasks (i.e., texts produced by non-native speakers) and data augmentation (i.e., native texts). To alleviate this issue, we propose to use an alternative data source, translationese (i.e., human-translated texts), as input for GEC data augmentation, which 1) is easier to obtain and usually has better quality than non-native texts, and 2) has a more similar style to non-native texts. Experimental results on the CoNLL14 and BEA19 English, NLPCC18 Chinese, Falko-MERLIN German, and RULEC-GEC Russian GEC benchmarks show that our approach consistently improves correction accuracy over strong baselines. Further analyses reveal that our approach is helpful for overcoming mainstream correction difficulties such as the corrections of frequent words, missing words, and substitution errors. Data, code, models and scripts are freely available at https://github.com/NLP2CT/TransGEC.

pdf bib
G-Tuning: Improving Generalization of Pre-trained Language Models with Generative Adversarial Network
Rongxiang Weng | Wen Sen Cheng | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

The generalization ability of pre-trained language models (Plms) in downstream tasks is heavily influenced by fine-tuning. The objective of fine-tuning is to transform the latent representation of Plms from a universal space to a target space, allowing the model to be applied to downstream tasks with the capability of generalizing to unseen samples. However, the effect of Plms will be diminished when the training data coverage is insufficient, in which fine-tuning is inadequate to learn the complete mapping. In this study, we propose a new fine-tuning framework, referred to as G-Tuning, that aims to preserve the generalization ability of Plms in downstream tasks. Specifically, we integrate a generative adversarial network into the fine-tuning process to aid in the transformation of the latent representation in the entire space. Empirical evaluations on the GLUE benchmark, as well as two additional demanding scenarios involving domain and language generalization, demonstrate that G-Tuning can accurately map the universal representation to the target space, thus effectively enhancing the generalization performance of Plms across various downstream tasks.

pdf bib
Language Anisotropic Cross-Lingual Model Editing
Yang Xu | Yutai Hou | Wanxiang Che | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Multilingual pre-trained language models can learn task-specific abilities or memorize facts across multiple languages but inevitably make undesired predictions with specific inputs. Under similar observation, model editing aims to post-hoc calibrate a model targeted to specific inputs with keeping the model’s raw behavior. However, existing work only studies the monolingual scenario, which lacks the cross-lingual transferability to perform editing simultaneously across languages. In this work, we focus on cross-lingual model editing. Firstly, we define the cross-lingual model editing task and corresponding metrics, where an edit in one language propagates to the others. Next, we propose a framework to naturally adapt monolingual model editing approaches to the cross-lingual scenario using parallel corpus. Further, we propose language anisotropic editing to improve cross-lingual editing by amplifying different subsets of parameters for each language. On the newly defined cross-lingual model editing task, we empirically demonstrate the failure of monolingual baselines in propagating the edit to multiple languages and the effectiveness of the proposed language anisotropic model editing. Our code is publicly available at https://github.com/franklear/LiME.

pdf bib
Rethinking Document-Level Relation Extraction: A Reality Check
Jing Li | Yequan Wang | Shuai Zhang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Recently, numerous efforts have continued to push up performance boundaries of document-level relation extraction (DocRE) and have claimed significant progress in DocRE. In this paper, we do not aim at proposing a novel model for DocRE. Instead, we take a closer look at the field to see if these performance gains are actually true. By taking a comprehensive literature review and a thorough examination of popular DocRE datasets, we find that these performance gains are achieved upon a strong or even untenable assumption in common: all named entities are perfectly localized, normalized, and typed in advance. Next, we construct four types of entity mention attacks to examine the robustness of typical DocRE models by behavioral probing. We also have a close check on model usability in a more realistic setting. Our findings reveal that most of current DocRE models are vulnerable to entity mention attacks and difficult to be deployed in real-world end-user NLP applications. Our study calls more attentions for future research to stop simplifying problem setups, and to model DocRE in the wild rather than in an unrealistic Utopian world.

pdf bib
Towards Better Hierarchical Text Classification with Data Generation
Yue Wang | Dan Qiao | Juntao Li | Jinxiong Chang | Qishen Zhang | Zhongyi Liu | Guannan Zhang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Hierarchical text classification (HTC) focuses on classifying one text into multiple labels, which are organized as a hierarchical taxonomy. Due to its wide involution in realistic scenarios, HTC attracts long-term attention from both industry and academia. However, the high cost of hierarchical multi-label annotation makes HTC suffer from the data scarcity problem. In view of the difficulty in balancing the controllability of multiple structural labels and text diversity, automatically generating high-quality data for HTC is challenging and under-explored. To fill this blank, we propose a novel data generation framework tailored for HTC, which can achieve both label controllability and text diversity by extracting high-quality semantic-level and phrase-level hierarchical label information. Experimental results on three benchmarks demonstrate that, compared with existing data augmentation methods, the data generated from our method can bring the most significant performance improvements of several strong HTC models. Extensive analysis confirms that the improvements yielded by our proposed method do correlate to the enhancement of label controllability and text diversity.

pdf bib
Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Hao Fei | Meishan Zhang | Min Zhang | Tat-Seng Chua
Findings of the Association for Computational Linguistics: ACL 2023

Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e.g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages. In this work, we investigate an unbiased UD- based XRE transfer by constructing a type of code-mixed UD forest. We first translate the sentence of the source language to the parallel target-side language, for both of which we parse the UD tree respectively. Then, we merge the source-/target-side UD structures as a unified code-mixed UD forest. With such forest features, the gaps of UD-based XRE between the training and predicting phases can be effectively closed. We conduct experiments on the ACE XRE benchmark datasets, where the results demonstrate that the proposed code-mixed UD forests help unbiased UD-based XRE transfer, with which we achieve significant XRE performance gains.

pdf bib
A Pilot Study on Dialogue-Level Dependency Parsing for Chinese
Gongyao Jiang | Shuang Liu | Meishan Zhang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Dialogue-level dependency parsing has received insufficient attention, especially for Chinese. To this end, we draw on ideas from syntactic dependency and rhetorical structure theory (RST), developing a high-quality human-annotated corpus, which contains 850 dialogues and 199,803 dependencies. Considering that such tasks suffer from high annotation costs, we investigate zero-shot and few-shot scenarios. Based on an existing syntactic treebank, we adopt a signal-based method to transform seen syntactic dependencies into unseen ones between elementary discourse units (EDUs), where the signals are detected by masked language modeling. Besides, we apply single-view and multi-view data selection to access reliable pseudo-labeled instances. Experimental results show the effectiveness of these baselines. Moreover, we discuss several crucial points about our dataset and approach.

pdf bib
NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts
Yue Zhang | Bo Zhang | Haochen Jiang | Zhenghua Li | Chen Li | Fei Huang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains. Previous CGEC research primarily focuses on correcting texts from a single domain, especially learner essays. To broaden the target domain, we annotate multiple references for 12,500 sentences from three native domains, i.e., social media, scientific writing, and examination. We provide solid benchmark results for NaSGEC by employing cutting-edge CGEC models and different training data. We further perform detailed analyses of the connections and gaps between our domains from both empirical and statistical views. We hope this work can inspire future studies on an important but under-explored direction–cross-domain GEC.

pdf bib
Disambiguated Lexically Constrained Neural Machine Translation
Jinpeng Zhang | Nini Xiao | Ke Wang | Chuanqi Dong | Xiangyu Duan | Yuqi Zhang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Lexically constrained neural machine translation (LCNMT), which controls the translation generation with pre-specified constraints, is important in many practical applications. Current approaches to LCNMT typically assume that the pre-specified lexicon constraints are contextually appropriate. This assumption limits their application to real-world scenarios where a source lexicon may have multiple target constraints, and disambiguation is needed to select the most suitable one. In this paper, we propose disambiguated LCNMT (D-LCNMT) to solve the problem. D-LCNMT is a robust and effective two-stage framework that disambiguates the constraints based on contexts at first, then integrates the disambiguated constraints into LCNMT. Experimental results show that our approach outperforms strong baselines including existing data argumentation based approaches on benchmark datasets, and comprehensive experiments in scenarios where a source lexicon corresponds to multiple target constraints demonstrate the constraint disambiguation superiority of our approach.

pdf bib
Can Diffusion Model Achieve Better Performance in Text Generation ? Bridging the Gap between Training and Inference !
Zecheng Tang | Pinzheng Wang | Keyan Zhou | Juntao Li | Ziqiang Cao | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward process during inference. Thus, the model only predicts based on the previously generated reverse noise rather than the noise computed by the forward process. Besides, the widely-used downsampling strategy in speeding up the inference will cause the mismatch of diffusion trajectories between training and inference. To understand and mitigate the above two types of training-inference discrepancies, we launch a thorough preliminary study. Based on our observations, we propose two simple yet effective methods to bridge the gaps mentioned above, named Distance Penalty and Adaptive Decay Sampling. Extensive experiments on 6 generation tasks confirm the superiority of our methods, which can achieve 100× → 200× speedup with better performance. Our code will be released at https://github.com/CODINNLG/Bridge_Gap_Diffusion.

pdf bib
Early Exit with Disentangled Representation and Equiangular Tight Frame
Yixin Ji | Jikai Wang | Juntao Li | Qiang Chen | Wenliang Chen | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Dynamic early exit has demonstrated great potential in coping with the sharply increasing number of pre-trained language model parameters, which can achieve a good trade-off between performance and efficiency. The existing early exit paradigm relies on training parametrical internal classifiers at each intermediate layer to complete specific tasks. Based on the predictions of these internal classifiers, different methods are designed to decide when to exit. Under this circumstance, each intermediate layer takes on both generic language representation learning and task-specific feature extraction, which makes each intermediate layer struggle to balance two types of backward loss signals during training. To break this dilemma, we propose an adapter method to decouple the two distinct types of representation and further introduce a non-parametric simplex equiangular tight frame classifier (ETF) for improvement. Extensive experiments on monolingual and multilingual tasks demonstrate that our method gains significant improvements over strong PLM backbones and early exit methods.

pdf bib
ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination
Dongfang Li | Jindi Yu | Baotian Hu | Zhenran Xu | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

In the field of Large Language Models (LLMs), researchers are increasingly exploring their effectiveness across a wide range of tasks. However, a critical area that requires further investigation is the interpretability of these models, particularly the ability to generate rational explanations for their decisions. Most existing explanation datasets are limited to the English language and the general domain, which leads to a scarcity of linguistic diversity and a lack of resources in specialized domains, such as medical. To mitigate this, we propose ExplainCPE, a challenging medical dataset consisting of over 7K problems from Chinese Pharmacist Examination, specifically tailored to assess the model-generated explanations. From the overall results, only GPT-4 passes the pharmacist examination with a 75.7% accuracy, while other models like ChatGPT fail. Further detailed analysis of LLM-generated explanations reveals the limitations of LLMs in understanding medical text and executing computational reasoning. With the increasing importance of AI safety and trustworthiness, ExplainCPE takes a step towards improving and evaluating the interpretability of LLMs in the medical domain.

pdf bib
G-SPEED: General SParse Efficient Editing MoDel
Haoke Zhang | Yue Wang | Juntao Li | Xiabing Zhou | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Large Language Models (LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages. Through human-model interactions, LLMs can automatically understand human-issued instructions and output the expected contents, which can significantly increase working efficiency. In various types of real-world demands, editing-oriented tasks account for a considerable proportion, which involves an interactive process that entails the continuous refinement of existing texts to meet specific criteria. Due to the need for multi-round human-model interaction and the generation of complicated editing tasks, there is an emergent need for efficient general editing models. In this paper, we propose General SParse Efficient Editing MoDel (G-SPEED), which can fulfill diverse editing requirements through a single model while maintaining low computational costs. Specifically, we first propose a novel unsupervised text editing data clustering algorithm to deal with the data scarcity problem. Subsequently, we introduce a sparse editing model architecture to mitigate the inherently limited learning capabilities of small language models. The experimental outcomes indicate that G-SPEED, with its 508M parameters, can surpass LLMs equipped with 175B parameters. Our code and model checkpoints are available at https://github.com/Banner-Z/G-SPEED.

pdf bib
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction
Xilai Ma | Jing Li | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Few-shot relation extraction involves identifying the type of relationship between two specific entities within a text, using a limited number of annotated samples. A variety of solutions to this problem have emerged by applying meta-learning and neural graph techniques which typically necessitate a training process for adaptation. Recently, the strategy of in-context learning has been demonstrating notable results without the need of training. Few studies have already utilized in-context learning for zero-shot information extraction. Unfortunately, the evidence for inference is either not considered or implicitly modeled during the construction of chain-of-thought prompts. In this paper, we propose a novel approach for few-shot relation extraction using large language models, named CoT-ER, chain-of-thought with explicit evidence reasoning. In particular, CoT-ER first induces large language models to generate evidences using task-specific and concept-level knowledge. Then these evidences are explicitly incorporated into chain-of-thought prompting for relation extraction. Experimental results demonstrate that our CoT-ER approach (with 0% training data) achieves competitive performance compared to the fully-supervised (with 100% training data) state-of-the-art approach on the FewRel1.0 and FewRel2.0 datasets.

pdf bib
Towards Making the Most of ChatGPT for Machine Translation
Keqin Peng | Liang Ding | Qihuang Zhong | Li Shen | Xuebo Liu | Min Zhang | Yuanxin Ouyang | Dacheng Tao
Findings of the Association for Computational Linguistics: EMNLP 2023

ChatGPT shows remarkable capabilities for machine translation (MT). Several prior studies have shown that it achieves comparable results to commercial systems for high-resource languages, but lags behind in complex tasks, e.g, low-resource and distant-language-pairs translation. However, they usually adopt simple prompts which can not fully elicit the capability of ChatGPT. In this report, we aim to further mine ChatGPT’s translation ability by revisiting several aspects: temperature, task information, and domain information, and correspondingly propose two (simple but effective) prompts: Task-Specific Prompts (TSP) and Domain-Specific Prompts (DSP). We show that: 1) The performance of ChatGPT depends largely on temperature, and a lower temperature usually can achieve better performance; 2) Emphasizing the task information further improves ChatGPT’s performance, particularly in complex MT tasks; 3) Introducing domain information can elicit ChatGPT’s generalization ability and improve its performance in the specific domain; 4) ChatGPT tends to generate hallucinations for non-English-centric MT tasks, which can be partially addressed by our proposed prompts but still need to be highlighted for the MT/NLP community. We also explore the effects of advanced in-context learning strategies and find a (negative but interesting) observation: the powerful chain-of-thought prompt leads to word-by-word translation behavior, thus bringing significant translation degradation.

pdf bib
Efficient Continue Training of Temporal Language Model with Structural Information
Zhaochen Su | Juntao Li | Zikang Zhang | Zihan Zhou | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Current language models are mainly trained on snap-shots of data gathered at a particular time, which decreases their capability to generalize over time and model language change. To model the time variable, existing works have explored temporal language models (e.g., TempoBERT) by directly incorporating the timestamp into the training process. While effective to some extent, these methods are limited by the superficial temporal information brought by timestamps, which fails to learn the inherent changes of linguistic components. In this paper, we empirically confirm that the performance of pre-trained language models (PLMs) is closely affiliated with syntactically changed tokens. Based on this observation, we propose a simple yet effective method named Syntax-Guided Temporal Language Model (SG-TLM), which could learn the inherent language changes by capturing an intrinsic relationship between the time prefix and the tokens with salient syntactic change. Experiments on two datasets and three tasks demonstrate that our model outperforms existing temporal language models in both memorization and generalization capabilities. Extensive results further confirm the effectiveness of our approach across different model frameworks, including both encoder-only and decoder-only models (e.g., LLaMA). Our code is available at https://github.com/zhaochen0110/TempoLM.

pdf bib
An Empirical Study of Frame Selection for Text-to-Video Retrieval
Mengxia Wu | Min Cao | Yang Bai | Ziyin Zeng | Chen Chen | Liqiang Nie | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video contexts, existing methods typically select a subset of frames within a video to represent the video content for TVR. How to select the most representative frames is a crucial issue, whereby the selected frames are required to not only retain the semantic information of the video but also promote retrieval efficiency by excluding temporally redundant frames. In this paper, we make the first empirical study of frame selection for TVR. We systemically classify existing frame selection methods into text-free and text-guided ones, under which we detailedly analyze six different frame selections in terms of effectiveness and efficiency. Among them, two frame selections are first developed in this paper. According to the comprehensive analysis on multiple TVR benchmarks, we empirically conclude that the TVR with proper frame selections can significantly improve the retrieval efficiency without sacrificing the retrieval performance.

pdf bib
Improving Seq2Seq Grammatical Error Correction via Decoding Interventions
Houquan Zhou | Yumeng Liu | Zhenghua Li | Min Zhang | Bo Zhang | Chen Li | Ji Zhang | Fei Huang
Findings of the Association for Computational Linguistics: EMNLP 2023

The sequence-to-sequence (Seq2Seq) approach has recently been widely used in grammatical error correction (GEC) and shows promising performance. However, the Seq2Seq GEC approach still suffers from two issues. First, a Seq2Seq GEC model can only be trained on parallel data, which, in GEC task, is often noisy and limited in quantity. Second, the decoder of a Seq2Seq GEC model lacks an explicit awareness of the correctness of the token being generated. In this paper, we propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally, and then dynamically influence the choice of the next token. We discover and investigate two types of critics: a pre-trained left-to-right language model critic and an incremental target-side grammatical error detector critic. Through extensive experiments on English and Chinese datasets, our framework consistently outperforms strong baselines and achieves results competitive with state-of-the-art methods.

pdf bib
SmartSpanNER: Making SpanNER Robust in Low Resource Scenarios
Min Zhang | Xiaosong Qiao | Yanqing Zhao | Shimin Tao | Hao Yang
Findings of the Association for Computational Linguistics: EMNLP 2023

Named Entity Recognition (NER) is one of the most fundamental tasks in natural language processing. Span-level prediction (SpanNER) is more naturally suitable for nested NER than sequence labeling (SeqLab). However, according to our experiments, the SpanNER method is more sensitive to the amount of training data, i.e., the F1 score of SpanNER drops much more than that of SeqLab when the amount of training data drops. In order to improve the robustness of SpanNER in low resource scenarios, we propose a simple and effective method SmartSpanNER, which introduces a Named Entity Head (NEH) prediction task to SpanNER and performs multi-task learning together with the task of span classification. Experimental results demonstrate that the robustness of SpanNER could be greatly improved by SmartSpanNER in low resource scenarios constructed on the CoNLL03, Few-NERD, GENIA and ACE05 standard benchmark datasets.

pdf bib
Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models
Yixin Ji | Jikai Wang | Juntao Li | Hai Ye | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

With the development of multilingual pre-trained language models (mPLMs), zero-shot cross-lingual transfer shows great potential. To further improve the performance of cross-lingual transfer, many studies have explored representation misalignment caused by morphological differences but neglected the misalignment caused by the anisotropic distribution of contextual representations. In this work, we propose enhanced isotropy and constrained code-switching for zero-shot cross-lingual transfer to alleviate the problem of misalignment caused by the anisotropic representations and maintain syntactic structural knowledge. Extensive experiments on three zero-shot cross-lingual transfer tasks demonstrate that our method gains significant improvements over strong mPLM backbones and further improves the state-of-the-art methods.

pdf bib
Isotropy-Enhanced Conditional Masked Language Models
Pei Guo | Yisheng Xiao | Juntao Li | Yixin Ji | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Non-autoregressive models have been widely used for various text generation tasks to accelerate the inference process but at the cost of generation quality to some extent. To achieve a good balance between inference speedup and generation quality, iterative NAR models like CMLM and Disco are proposed. Researchers have made much follow-up progress based on them, and some recent iterative models can achieve very promising performance while maintaining significant speedup. In this paper, we give more insights into iterative NAR models by exploring the anisotropic problem, i.e., the representations of distinct predicted target tokens are similar and indiscriminative. Upon the confirmation of the anisotropic problem in iterative NAR models, we first analyze the effectiveness of the contrastive learning method and further propose the Look Neighbors strategy to enhance the learning of token representations during training. Experiments on 4 WMT datasets show that our methods consistently improve the performance as well as alleviate the anisotropic problem of the conditional masked language model, even outperforming the current SoTA result on WMT14 EN DE.

pdf bib
Scaling Law for Document Neural Machine Translation
Zhang Zhuocheng | Shuhao Gu | Min Zhang | Yang Feng
Findings of the Association for Computational Linguistics: EMNLP 2023

The scaling laws of language models have played a significant role in advancing large language models. In order to promote the development of document translation, we systematically examine the scaling laws in this field. In this paper, we carry out an in-depth analysis of the influence of three factors on translation quality: model scale, data scale, and sequence length. Our findings reveal that increasing sequence length effectively enhances model performance when model size is limited. However, sequence length cannot be infinitely extended; it must be suitably aligned with the model scale and corpus volume. Further research shows that providing adequate context can effectively enhance the translation quality of a document’s initial portion. Nonetheless, exposure bias remains the primary factor hindering further improvement in translation quality for the latter half of the document.

pdf bib
Improving Low-resource Question Answering by Augmenting Question Information
Andong Chen | Yuan Sun | Xiaobing Zhao | Rosella Galindo Esparza | Kehai Chen | Yang Xiang | Tiejun Zhao | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

In the era of large models, low-resource question-answering tasks lag, emphasizing the importance of data augmentation - a key research avenue in natural language processing. The main challenges include leveraging the large model’s internal knowledge for data augmentation, determining which QA data component - the question, passage, or answer - benefits most from augmentation, and retaining consistency in the augmented content without inducing excessive noise. To tackle these, we introduce PQQ, an innovative approach for question data augmentation consisting of Prompt Answer, Question Generation, and Question Filter. Our experiments reveal that ChatGPT underperforms on the experimental data, yet our PQQ method excels beyond existing augmentation strategies. Further, its universal applicability is validated through successful tests on high-resource QA tasks like SQUAD1.1 and TriviaQA.

pdf bib
Addressing the Length Bias Challenge in Document-Level Neural Machine Translation
Zhang Zhuocheng | Shuhao Gu | Min Zhang | Yang Feng
Findings of the Association for Computational Linguistics: EMNLP 2023

Document-level neural machine translation (DNMT) has shown promising results by incorporating context information through increased maximum lengths of source and target sentences. However, this approach also introduces a length bias problem, whereby DNMT suffers from significant translation quality degradation when decoding sentences that are much shorter or longer than the maximum sentence length during training, i.e., the length bias problem. To prevent the model from neglecting shorter sentences, we sample the training data to ensure a more uniform distribution across different sentence lengths while progressively increasing the maximum sentence length during training. Additionally, we introduce a length-normalized attention mechanism to aid the model in focusing on target information, mitigating the issue of attention divergence when processing longer sentences. Furthermore, during the decoding stage of DNMT, we propose a sliding decoding strategy that limits the length of target sentences to not exceed the maximum length encountered during training. The experimental results indicate that our method can achieve state-of-the-art results on several open datasets, and further analysis shows that our method can significantly alleviate the length bias problem.

pdf bib
A Read-and-Select Framework for Zero-shot Entity Linking
Zhenran Xu | Yulin Chen | Baotian Hu | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Zero-shot entity linking (EL) aims at aligning entity mentions to unseen entities to challenge the generalization ability. Previous methods largely focus on the candidate retrieval stage and ignore the essential candidate ranking stage, which disambiguates among entities and makes the final linking prediction. In this paper, we propose a read-and-select (ReS) framework by modeling the main components of entity disambiguation, i.e., mention-entity matching and cross-entity comparison. First, for each candidate, the reading module leverages mention context to output mention-aware entity representations, enabling mention-entity matching. Then, in the selecting module, we frame the choice of candidates as a sequence labeling problem, and all candidate representations are fused together to enable cross-entity comparison. Our method achieves the state-of-the-art performance on the established zero-shot EL dataset ZESHEL with a 2.55% micro-average accuracy gain, with no need for laborious multi-phase pre-training used in most of the previous work, showing the effectiveness of both mention-entity and cross-entity interaction.

pdf bib
Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation
Zhongjian Miao | Wen Zhang | Jinsong Su | Xiang Li | Jian Luan | Yidong Chen | Bin Wang | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Conventional knowledge distillation(KD) approaches are commonly employed to compress neural machine translation(NMT) models. However, they only obtain one lightweight student each time. Consequently, we have to conduct KD multiple times when different students are required at the same time, which could be resource-intensive. Additionally, these students are individually optimized, and thus lack interactions with each other, leading to their potential not being fully exerted. In this work, we propose a novel All-In-One Knowledge Distillation(AIO-KD) framework for NMT, which generates multiple satisfactory students at once. Under AIO-KD, we first randomly extract fewer-layer subnetworks from the teacher as the sample students. Then, we jointly optimize the teacher and these students, where the students simultaneously learn the knowledge from the teacher and interact with other students via mutual learning. When utilized, we re-extract the candidate students, satisfying the specifications of various devices. Particularly, we adopt carefully-designed strategies for AIO-KD: 1) we dynamically detach gradients to prevent poorly-performed students from negatively affecting the teacher during the knowledge transfer, which could subsequently impact other students; 2) we design a two-stage mutual learning strategy, which alleviates the negative impacts of poorly-performed students on the early-stage student interactions. Extensive experiments and in-depth analyses on three benchmarks demonstrate the effectiveness and eco-friendliness of AIO-KD. Our source code is available at https://github.com/DeepLearnXMU/AIO-KD.

pdf bib
INFORM : Information eNtropy based multi-step reasoning FOR large language Models
Chuyue Zhou | Wangjie You | Juntao Li | Jing Ye | Kehai Chen | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Large language models (LLMs) have demonstrated exceptional performance in reasoning tasks with dedicated Chain-of-Thought (CoT) prompts. Further enhancing CoT prompts with exquisite exemplars can significantly improve reasoning performance.However, the effectiveness of CoT prompts may fluctuate dramatically with different choices of in-context examples. Additionally, manual construction of rationale steps can be time-consuming, presenting challenges for the widespread adoption of CoT prompting. In this work, we propose a novel approach by introducing information entropy (IE) as a criteria on for CoT prompt selection. We extend this criterion to the CoT generation and inference stages, automatically generating CoT prompts with higher information entropy scores and adaptively determining the number of samples. These three stages together form our proposed information- entropy-based multi-step reasoning for large language models, named INFORM. Our experiments across seven reasoning benchmarks utilizing two language models(GPT-3.5-Turbo and text-davinci-003) demonstrate the superiority of INFORM both in performance and efficiency.

pdf bib
Non-autoregressive Streaming Transformer for Simultaneous Translation
Zhengrui Ma | Shaolei Zhang | Shoutao Guo | Chenze Shao | Min Zhang | Yang Feng
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality. However, training these models to achieve high quality while maintaining low latency often leads to a tendency for aggressive anticipation. We argue that such issue stems from the autoregressive architecture upon which most existing SiMT models are built. To address those issues, we propose non-autoregressive streaming Transformer (NAST) which comprises a unidirectional encoder and a non-autoregressive decoder with intra-chunk parallelism. We enable NAST to generate the blank token or repetitive tokens to adjust its READ/WRITE strategy flexibly, and train it to maximize the non-monotonic latent alignment with an alignment-based latency loss. Experiments on various SiMT benchmarks demonstrate that NAST outperforms previous strong autoregressive SiMT baselines.

pdf bib
LLM-enhanced Self-training for Cross-domain Constituency Parsing
Jianling Li | Meishan Zhang | Peiming Guo | Min Zhang | Yue Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Self-training has proven to be an effective approach for cross-domain tasks, and in this study, we explore its application to cross-domain constituency parsing. Traditional self-training methods rely on limited and potentially low-quality raw corpora. To overcome this limitation, we propose enhancing self-training with the large language model (LLM) to generate domain-specific raw corpora iteratively. For the constituency parsing, we introduce grammar rules that guide the LLM in generating raw corpora and establish criteria for selecting pseudo instances. Our experimental results demonstrate that self-training for constituency parsing, equipped with an LLM, outperforms traditional methods regardless of the LLM’s performance. Moreover, the combination of grammar rules and confidence criteria for pseudo-data selection yields the highest performance in the cross-domain constituency parsing.

pdf bib
Mirror: A Universal Framework for Various Information Extraction Tasks
Tong Zhu | Junfei Ren | Zijian Yu | Mengsong Wu | Guoliang Zhang | Xiaoye Qu | Wenliang Chen | Zhefeng Wang | Baoxing Huai | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Sharing knowledge between information extraction tasks has always been a challenge due to the diverse data formats and task variations. Meanwhile, this divergence leads to information waste and increases difficulties in building complex applications in real scenarios. Recent studies often formulate IE tasks as a triplet extraction problem. However, such a paradigm does not support multi-span and n-ary extraction, leading to weak versatility. To this end, we reorganize IE problems into unified multi-slot tuples and propose a universal framework for various IE tasks, namely Mirror. Specifically, we recast existing IE tasks as a multi-span cyclic graph extraction problem and devise a non-autoregressive graph decoding algorithm to extract all spans in a single step. It is worth noting that this graph structure is incredibly versatile, and it supports not only complex IE tasks, but also machine reading comprehension and classification tasks. We manually construct a corpus containing 57 datasets for model pretraining, and conduct experiments on 30 datasets across 8 downstream tasks. The experimental results demonstrate that our model has decent compatibility and outperforms or reaches competitive performance with SOTA systems under few-shot and zero-shot settings. The code, model weights, and pretraining corpus are available at https://github.com/Spico197/Mirror .

pdf bib
PromptST: Abstract Prompt Learning for End-to-End Speech Translation
Tengfei Yu | Liang Ding | Xuebo Liu | Kehai Chen | Meishan Zhang | Dacheng Tao | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

An end-to-end speech-to-text (S2T) translation model is usually initialized from a pre-trained speech recognition encoder and a pre-trained text-to-text (T2T) translation decoder. Although this straightforward setting has been shown empirically successful, there do not exist clear answers to the research questions: 1) how are speech and text modalities fused in S2T model and 2) how to better fuse the two modalities? In this paper, we take the first step toward understanding the fusion of speech and text features in S2T model. We first design and release a 10GB linguistic probing benchmark, namely Speech-Senteval, to investigate the acoustic and linguistic behaviors of S2T models. Preliminary analysis reveals that the uppermost encoder layers of the S2T model can not learn linguistic knowledge efficiently, which is crucial for accurate translation. Based on the finding, we further propose a simple plug-in prompt-learning strategy on the uppermost encoder layers to broaden the abstract representation power of the encoder of S2T models. We call such a prompt-enhanced S2T model PromptST. Experimental results on four widely-used S2T datasets show that PromptST can deliver significant improvements over a strong baseline by capturing richer linguistic knowledge. Benchmarks, code, and scripts are freely available at https://github.com/ytf-philp/PromptST.

pdf bib
Revisiting Sparse Retrieval for Few-shot Entity Linking
Yulin Chen | Zhenran Xu | Baotian Hu | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Entity linking aims to link ambiguous mentions to their corresponding entities in a knowledge base. One of the key challenges comes from insufficient labeled data for specific domains. Although dense retrievers have achieved excellent performance on several benchmarks, their performance decreases significantly when only a limited amount of in-domain labeled data is available. In such few-shot setting, we revisit the sparse retrieval method, and propose an ELECTRA-based keyword extractor to denoise the mention context and construct a better query expression. For training the extractor, we propose a distant supervision method to automatically generate training data based on overlapping tokens between mention contexts and entity descriptions. Experimental results on the ZESHEL dataset demonstrate that the proposed method outperforms state-of-the-art models by a significant margin across all test domains, showing the effectiveness of keyword-enhanced sparse retrieval.

pdf bib
Beware of Model Collapse! Fast and Stable Test-time Adaptation for Robust Question Answering
Yi Su | Yixin Ji | Juntao Li | Hai Ye | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Although pre-trained language models (PLM) have achieved great success in question answering (QA), their robustness is still insufficient to support their practical applications, especially in the face of distribution shifts. Recently, test-time adaptation (TTA) has shown great potential for solving this problem, which adapts the model to fit the test samples at test time. However, TTA sometimes causes model collapse, making almost all the model outputs incorrect, which has raised concerns about its stability and reliability. In this paper, we delve into why TTA causes model collapse and find that the imbalanced label distribution inherent in QA is the reason for it. To address this problem, we propose Anti-Collapse Fast test-time adaptation (Anti-CF), which utilizes the source model‘s output to regularize the update of the adapted model during test time. We further design an efficient side block to reduce its inference time. Extensive experiments on various distribution shift scenarios and pre-trained language models (e.g., XLM-RoBERTa, BLOOM) demonstrate that our method can achieve comparable or better results than previous TTA methods at a speed close to vanilla forward propagation, which is 1.8× to 4.4× speedup compared to previous TTA methods.

pdf bib
Empower Nested Boolean Logic via Self-Supervised Curriculum Learning
Hongqiu Wu | Linfeng Liu | Hai Zhao | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data. As opposed to constructing increasingly complex logic, this paper probes into the boolean logic, the root capability of a logical reasoner. We find that any pre-trained language models even including large language models only behave like a random selector in the face of multi-nested boolean logic, a task that humans can handle with ease. To empower language models with this fundamental capability, this paper proposes a new self-supervised learning method Curriculum Logical Reasoning (Clr), where we augment the training data with nested boolean logic chain step-by-step, and program the training from simpler logical patterns gradually to harder ones. This new training paradigm allows language models to effectively generalize to much harder and longer-hop logic, which can hardly be learned through naive training. Furthermore, we show that boolean logic is a great foundation for improving the subsequent general logical tasks.

pdf bib
Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix
Xinyu Ma | Xuebo Liu | Min Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

In multilingual translation research, the comprehension and utilization of language families are of paramount importance. Nevertheless, clustering languages based solely on their ancestral families can yield suboptimal results due to variations in the datasets employed during the model’s training phase. To mitigate this challenge, we introduce an innovative method that leverages the fisher information matrix (FIM) to cluster language families, anchored on the multilingual translation model’s characteristics. We hypothesize that language pairs with similar effects on model parameters exhibit a considerable degree of linguistic congruence and should thus be grouped cohesively. This concept has led us to define pseudo language families. We provide an in-depth discussion regarding the inception and application of these pseudo language families. Empirical evaluations reveal that employing these pseudo language families enhances performance over conventional language families in adapting a multilingual translation model to unfamiliar language pairs. The proposed methodology may also be extended to scenarios requiring language similarity measurements. The source code and associated scripts can be accessed at https://github.com/ecoli-hit/PseudoFamily.

pdf bib
CCL23-Eval 任务3系统报告:苏州大学CFSP系统(System Report for CCL23-Eval Task3: SUDA CFSP System)
Yahui Liu (刘亚慧) | Zhenghua Li (李正华) | Min Zhang (张民)
Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)

“本文介绍了我们在第二十二届中国计算语言学大会汉语框架语义解析评测中提交的参赛系统。框架语义解析是自然语言处理领域中重要的任务,其目标是从句子中提取框架语义结构。本次评测任务针对汉语框架语义的三个子任务(框架识别、论元范围识别和论元角色识别)使用不同的端到端框架进行解析,并利用数据增强和投票方法进一步提高预测的精度,最终,在A榜测试集上取得第二名,B榜测试集上取得第三名。”

pdf bib
CCL23-Eval任务7赛道一系统报告:Suda &Alibaba 文本纠错系统(CCL23-Eval Task 7 Track 1 System Report: Suda &Alibaba Team Text Error Correction System)
Haochen Jiang (蒋浩辰) | Yumeng Liu (刘雨萌) | Houquan Zhou (周厚全) | Ziheng Qiao (乔子恒) | Bo Zhang (波章,) | Chen Li (李辰) | Zhenghua Li (李正华) | Min Zhang (张民)
Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)

“本报告描述 Suda &Alibaba 纠错团队在 CCL2023 汉语学习者文本纠错评测任务的赛道一:多维度汉语学习者文本纠错(Multidimensional Chinese Learner Text Correc-tion)中提交的参赛系统。在模型方面,本队伍使用了序列到序列和序列到编辑两种纠错模型。在数据方面,本队伍分别使用基于混淆集构造的伪数据、Lang-8 真实数据以及 YACLC 开发集进行三阶段训练;在开放任务上还额外使用HSK、CGED等数据进行训练。本队伍还使用了一系列有效的性能提升技术,包括了基于规则的数据增强,数据清洗,后处理以及模型集成等 .除此之外,本队伍还在如何使用GPT3.5、GPT4等大模型来辅助中文文本纠错上进行了一些探索,提出了一种可以有效避免大模型过纠问题的方法,并尝试了多种 Prompt。在封闭和开放两个任务上,本队伍在最小改动、流利提升和平均 F0.5 得分上均位列第一。”

pdf bib
Empowering a Metric with LLM-assisted Named Entity Annotation: HW-TSC’s Submission to the WMT23 Metrics Shared Task
Zhanglin Wu | Yilun Liu | Min Zhang | Xiaofeng Zhao | Junhao Zhu | Ming Zhu | Xiaosong Qiao | Jingfei Zhang | Ma Miaomiao | Zhao Yanqing | Song Peng | Shimin Tao | Hao Yang | Yanfei Jiang
Proceedings of the Eighth Conference on Machine Translation

This paper presents the submission of Huawei Translation Service Center (HW-TSC) to the WMT23 metrics shared task, in which we submit two metrics: KG-BERTScore and HWTSC-EE-Metric. Among them, KG-BERTScore is our primary submission for the reference-free metric, which can provide both segment-level and system-level scoring. While HWTSC-EE-Metric is our primary submission for the reference-based metric, which can only provide system-level scoring. Overall, our metrics show relatively high correlations with MQM scores on the metrics tasks of previous years. Especially on system-level scoring tasks, our metrics achieve new state-of-the-art in many language pairs.

pdf bib
HW-TSC 2023 Submission for the Quality Estimation Shared Task
Yuang Li | Chang Su | Ming Zhu | Mengyao Piao | Xinglin Lyu | Min Zhang | Hao Yang
Proceedings of the Eighth Conference on Machine Translation

Quality estimation (QE) is an essential technique to assess machine translation quality without reference translations. In this paper, we focus on Huawei Translation Services Center’s (HW-TSC’s) submission to the sentence-level QE shared task, named Ensemble-CrossQE. Our system uses CrossQE, the same model architecture as our last year’s submission, which consists of a multilingual base model and a task-specific downstream layer. The input is the concatenation of the source and the translated sentences. To enhance the performance, we finetuned and ensembled multiple base models such as XLM-R, InfoXLM, RemBERT and CometKiwi. Moreover, we introduce a new corruption-based data augmentation method, which generates deletion, substitution and insertion errors in the original translation and uses a reference-based QE model to obtain pseudo scores. Results show that our system achieves impressive performance on sentence-level QE test sets and ranked the first place for three language pairs: English-Hindi, English-Tamil and English-Telegu. In addition, we participated in the error span detection task. The submitted model outperforms the baseline on Chinese-English and Hebrew-English language pairs.

pdf bib
HW-TSC’s Participation in the WMT 2023 Automatic Post Editing Shared Task
Jiawei Yu | Min Zhang | Zhao Yanqing | Xiaofeng Zhao | Yuang Li | Su Chang | Yinglu Li | Ma Miaomiao | Shimin Tao | Hao Yang
Proceedings of the Eighth Conference on Machine Translation

The paper presents the submission by HW-TSC in the WMT 2023 Automatic Post Editing (APE) shared task for the English-Marathi (En-Mr) language pair. Our method encompasses several key steps. First, we pre-train an APE model by utilizing synthetic APE data provided by the official task organizers. Then, we fine-tune the model by employing real APE data. For data augmentation, we incorporate candidate translations obtained from an external Machine Translation (MT) system. Furthermore, we integrate the En-Mr parallel corpus from the Flores-200 dataset into our training data. To address the overfitting issue, we employ R-Drop during the training phase. Given that APE systems tend to exhibit a tendency of ‘over-correction’, we employ a sentence-level Quality Estimation (QE) system to select the final output, deciding between the original translation and the corresponding output generated by the APE model. Our experiments demonstrate that pre-trained APE models are effective when being fine-tuned with the APE corpus of a limited size, and the performance can be further improved with external MT augmentation. Our approach improves the TER and BLEU scores on the development set by -2.42 and +3.76 points, respectively.

pdf bib
Leveraging Multilingual Knowledge Graph to Boost Domain-specific Entity Translation of ChatGPT
Min Zhang | Limin Liu | Zhao Yanqing | Xiaosong Qiao | Su Chang | Xiaofeng Zhao | Junhao Zhu | Ming Zhu | Song Peng | Yinglu Li | Yilun Liu | Wenbing Ma | Mengyao Piao | Shimin Tao | Hao Yang | Yanfei Jiang
Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track

Recently, ChatGPT has shown promising results for Machine Translation (MT) in general domains and is becoming a new paradigm for translation. In this paper, we focus on how to apply ChatGPT to domain-specific translation and propose to leverage Multilingual Knowledge Graph (MKG) to help ChatGPT improve the domain entity translation quality. To achieve this, we extract the bilingual entity pairs from MKG for the domain entities that are recognized from source sentences. We then introduce these pairs into translation prompts, instructing ChatGPT to use the correct translations of the domain entities. To evaluate the novel MKG method for ChatGPT, we conduct comparative experiments on three Chinese-English (zh-en) test datasets constructed from three specific domains, of which one domain is from biomedical science, and the other two are from the Information and Communications Technology (ICT) industry — Visible Light Communication (VLC) and wireless domains. Experimental results demonstrate that both the overall translation quality of ChatGPT (+6.21, +3.13 and +11.25 in BLEU scores) and the translation accuracy of domain entities (+43.2%, +30.2% and +37.9% absolute points) are significantly improved with MKG on the three test datasets.

pdf bib
KG-IQES: An Interpretable Quality Estimation System for Machine Translation Based on Knowledge Graph
Junhao Zhu | Min Zhang | Hao Yang | Song Peng | Zhanglin Wu | Yanfei Jiang | Xijun Qiu | Weiqiang Pan | Ming Zhu | Ma Miaomiao | Weidong Zhang
Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track

The widespread use of machine translation (MT) has driven the need for effective automatic quality estimation (AQE) methods. How to enhance the interpretability of MT output quality estimation is well worth exploring in the industry. From the perspective of the alignment of named entities (NEs) in the source and translated sentences, we construct a multilingual knowledge graph (KG) consisting of domain-specific NEs, and design a KG-based interpretable quality estimation (QE) system for machine translations (KG-IQES). KG-IQES effectively estimates the translation quality without relying on reference translations. Its effectiveness has been verified in our business scenarios.

2022

pdf bib
MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset
Yahui Liu | Haoping Yang | Chen Gong | Qingrong Xia | Zhenghua Li | Min Zhang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

During the past decade, neural network models have made tremendous progress on in-domain semantic role labeling (SRL). However, performance drops dramatically under the out-of-domain setting. In order to facilitate research on cross-domain SRL, this paper presents MuCPAD, a multi-domain Chinese predicate-argument dataset, which consists of 30,897 sentences and 92,051 predicates from six different domains. MuCPAD exhibits three important features. 1) Based on a frame-free annotation methodology, we avoid writing complex frames for new predicates. 2) We explicitly annotate omitted core arguments to recover more complete semantic structure, considering that omission of content words is ubiquitous in multi-domain Chinese texts. 3) We compile 53 pages of annotation guidelines and adopt strict double annotation for improving data quality. This paper describes in detail the annotation methodology and annotation process of MuCPAD, and presents in-depth data analysis. We also give benchmark results on cross-domain SRL based on MuCPAD.

pdf bib
MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction
Yue Zhang | Zhenghua Li | Zuyi Bao | Jiacheng Li | Bo Zhang | Chen Li | Fei Huang | Min Zhang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7,063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources. Each sentence is corrected by three annotators, and their corrections are carefully reviewed by a senior annotator, resulting in 2.3 references per sentence. We conduct experiments with two mainstream CGEC models, i.e., the sequence-to-sequence model and the sequence-to-edit model, both enhanced with large pretrained language models, achieving competitive benchmark performance on previous and our datasets. We also discuss CGEC evaluation methodologies, including the effect of multiple references and using a char-based metric. Our annotation guidelines, data, and code are available at https://github.com/HillZhang1999/MuCGEC.

pdf bib
Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting
Linzhi Wu | Pengjun Xie | Jie Zhou | Meishan Zhang | Ma Chunping | Guangwei Xu | Min Zhang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Self-augmentation has received increasing research interest recently to improve named entity recognition (NER) performance in low-resource scenarios. Token substitution and mixup are two feasible heterogeneous self-augmentation techniques for NER that can achieve effective performance with certain specialized efforts. Noticeably, self-augmentation may introduce potentially noisy augmented data. Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually. In this paper, we revisit these two typical self-augmentation methods for NER, and propose a unified meta-reweighting strategy for them to achieve a natural integration. Our method is easily extensible, imposing little effort on a specific self-augmentation method. Experiments on different Chinese and English NER benchmarks show that our token substitution and mixup method, as well as their integration, can achieve effective performance improvement. Based on the meta-reweighting mechanism, we can enhance the advantages of the self-augmentation techniques without much extra effort.

pdf bib
Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network
Ying Li | Shuaike Li | Min Zhang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Supervised parsing models have achieved impressive results on in-domain texts. However, their performances drop drastically on out-of-domain texts due to the data distribution shift. The shared-private model has shown its promising advantages for alleviating this problem via feature separation, whereas prior works pay more attention to enhance shared features but neglect the in-depth relevance of specific ones. To address this issue, we for the first time apply a dynamic matching network on the shared-private model for semi-supervised cross-domain dependency parsing. Meanwhile, considering the scarcity of target-domain labeled data, we leverage unlabeled data from two aspects, i.e., designing a new training strategy to improve the capability of the dynamic matching network and fine-tuning BERT to obtain domain-related contextualized representations. Experiments on benchmark datasets show that our proposed model consistently outperforms various baselines, leading to new state-of-the-art results on all domains. Detailed analysis on different matching strategies demonstrates that it is essential to learn suitable matching weights to emphasize useful features and ignore useless or even harmful ones. Besides, our proposed model can be directly extended to multi-source domain adaptation and achieves best performances among various baselines, further verifying the effectiveness and robustness.

pdf bib
Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing Annotations
Xin Zhang | Guangwei Xu | Yueheng Sun | Meishan Zhang | Xiaobin Wang | Min Zhang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent works of opinion expression identification (OEI) rely heavily on the quality and scale of the manually-constructed training corpus, which could be extremely difficult to satisfy. Crowdsourcing is one practical solution for this problem, aiming to create a large-scale but quality-unguaranteed corpus. In this work, we investigate Chinese OEI with extremely-noisy crowdsourcing annotations, constructing a dataset at a very low cost. Following Zhang el al. (2021), we train the annotator-adapter model by regarding all annotations as gold-standard in terms of crowd annotators, and test the model by using a synthetic expert, which is a mixture of all annotators. As this annotator-mixture for testing is never modeled explicitly in the training phase, we propose to generate synthetic training samples by a pertinent mixup strategy to make the training and testing highly consistent. The simulation experiments on our constructed dataset show that crowdsourcing is highly promising for OEI, and our proposed annotator-mixup can further enhance the crowdsourcing modeling.

pdf bib
Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation
Chulun Zhou | Fandong Meng | Jie Zhou | Min Zhang | Hongji Wang | Jinsong Su
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner. Although many previous studies try to incorporate global information into NMT models, there still exist limitations on how to effectively exploit bidirectional global context. In this paper, we propose a Confidence Based Bidirectional Global Context Aware (CBBGCA) training framework for NMT, where the NMT model is jointly trained with an auxiliary conditional masked language model (CMLM). The training consists of two stages: (1) multi-task joint training; (2) confidence based knowledge distillation. At the first stage, by sharing encoder parameters, the NMT model is additionally supervised by the signal from the CMLM decoder that contains bidirectional global contexts. Moreover, at the second stage, using the CMLM as teacher, we further pertinently incorporate bidirectional global context to the NMT model on its unconfidently-predicted target words via knowledge distillation. Experimental results show that our proposed CBBGCA training framework significantly improves the NMT model by +1.02, +1.30 and +0.57 BLEU scores on three large-scale translation datasets, namely WMT’14 English-to-German, WMT’19 Chinese-to-English and WMT’14 English-to-French, respectively.

pdf bib
RST Discourse Parsing with Second-Stage EDU-Level Pre-training
Nan Yu | Meishan Zhang | Guohong Fu | Min Zhang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU).To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP).We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective,leading a 2.1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.

pdf bib
Prediction Difference Regularization against Perturbation for Neural Machine Translation
Dengji Guo | Zhengrui Ma | Min Zhang | Yang Feng
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Regularization methods applying input perturbation have drawn considerable attention and have been frequently explored for NMT tasks in recent years. Despite their simplicity and effectiveness, we argue that these methods are limited by the under-fitting of training data. In this paper, we utilize prediction difference for ground-truth tokens to analyze the fitting of token-level samples and find that under-fitting is almost as common as over-fitting. We introduce prediction difference regularization (PD-R), a simple and effective method that can reduce over-fitting and under-fitting at the same time. For all token-level samples, PD-R minimizes the prediction difference between the original pass and the input-perturbed pass, making the model less sensitive to small input changes, thus more robust to both perturbations and under-fitted training data. Experiments on three widely used WMT translation tasks show that our approach can significantly improve over existing perturbation regularization methods. On WMT16 En-De task, our model achieves 1.80 SacreBLEU improvement over vanilla transformer.

pdf bib
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation
Bei Li | Quan Du | Tao Zhou | Yi Jing | Shuhan Zhou | Xin Zeng | Tong Xiao | JingBo Zhu | Xuebo Liu | Min Zhang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE). This paper explores a deeper relationship between Transformer and numerical ODE methods. We first show that a residual block of layers in Transformer can be described as a higher-order solution to ODE. Inspired by this, we design a new architecture, ODE Transformer, which is analogous to the Runge-Kutta method that is well motivated in ODE. As a natural extension to Transformer, ODE Transformer is easy to implement and efficient to use. Experimental results on the large-scale machine translation, abstractive summarization, and grammar error correction tasks demonstrate the high genericity of ODE Transformer. It can gain large improvements in model performance over strong baselines (e.g., 30.77 and 44.11 BLEU scores on the WMT’14 English-German and English-French benchmarks) at a slight cost in inference efficiency.

pdf bib
Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
Peijie Jiang | Dingkun Long | Yanzhao Zhang | Pengjun Xie | Meishan Zhang | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Boundary information is critical for various Chinese language processing tasks, such as word segmentation, part-of-speech tagging, and named entity recognition. Previous studies usually resorted to the use of a high-quality external lexicon, where lexicon items can offer explicit boundary information. However, to ensure the quality of the lexicon, great human effort is always necessary, which has been generally ignored. In this work, we suggest unsupervised statistical boundary information instead, and propose an architecture to encode the information directly into pre-trained language models, resulting in Boundary-Aware BERT (BABERT). We apply BABERT for feature induction of Chinese sequence labeling tasks. Experimental results on ten benchmarks of Chinese sequence labeling demonstrate that BABERT can provide consistent improvements on all datasets. In addition, our method can complement previous supervised lexicon exploration, where further improvements can be achieved when integrated with external lexicon information.

pdf bib
Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation
Yu Zhao | Jianguo Wei | ZhiChao Lin | Yueheng Sun | Meishan Zhang | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Image-to-text tasks such as open-ended image captioning and controllable image description have received extensive attention for decades. Here we advance this line of work further, presenting Visual Spatial Description (VSD), a new perspective for image-to-text toward spatial semantics. Given an image and two objects inside it, VSD aims to produce one description focusing on the spatial perspective between the two objects. Accordingly, we annotate a dataset manually to facilitate the investigation of the newly-introduced task, and then build several benchmark encoder-decoder models by using VL-BART and VL-T5 as backbones. In addition, we investigate visual spatial relationship classification (VSRC) information into our model by pipeline and end-to-end architectures. Finally, we conduct experiments on our benchmark dataset to evaluate all our models. Results show that our models are awe-inspiring, offering accurate and human-like spatial-oriented text descriptions. Besides, VSRC has great potential for VSD, and the joint end-to-end architecture is the better choice for their integration. We will make the dataset and codes publicly available for research purposes.

pdf bib
SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser
Yue Zhang | Bo Zhang | Zhenghua Li | Zuyi Bao | Chen Li | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

This work proposes a syntax-enhanced grammatical error correction (GEC) approach named SynGEC that effectively incorporates dependency syntactic information into the encoder part of GEC models. The key challenge for this idea is that off-the-shelf parsers are unreliable when processing ungrammatical sentences. To confront this challenge, we propose to build a tailored GEC-oriented parser (GOPar) using parallel GEC training data as a pivot. First, we design an extended syntax representation scheme that allows us to represent both grammatical errors and syntax in a unified tree structure. Then, we obtain parse trees of the source incorrect sentences by projecting trees of the target correct sentences. Finally, we train GOPar with such projected trees. For GEC, we employ the graph convolution network to encode source-side syntactic information produced by GOPar, and fuse them with the outputs of the Transformer encoder. Experiments on mainstream English and Chinese GEC datasets show that our proposed SynGEC approach consistently and substantially outperforms strong baselines and achieves competitive performance. Our code and data are all publicly available at https://github.com/HillZhang1999/SynGEC.

pdf bib
Modeling Consistency Preference via Lexical Chains for Document-level Neural Machine Translation
Xinglin Lyu | Junhui Li | Shimin Tao | Hao Yang | Ying Qin | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In this paper we aim to relieve the issue of lexical translation inconsistency for document-level neural machine translation (NMT) by modeling consistency preference for lexical chains, which consist of repeated words in a source-side document and provide a representation of the lexical consistency structure of the document. Specifically, we first propose lexical-consistency attention to capture consistency context among words in the same lexical chains. Then for each lexical chain we define and learn a consistency-tailored latent variable, which will guide the translation of corresponding sentences to enhance lexical translation consistency. Experimental results on Chinese→English and French→English document-level translation tasks show that our approach not only significantly improves translation performance in BLEU, but also substantially alleviates the problem of the lexical translation inconsistency.

pdf bib
Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change
Zhaochen Su | Zecheng Tang | Xinyan Guan | Lijun Wu | Min Zhang | Juntao Li
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., language model pre-trained on static data from past years performs worse over time on emerging data. Existing methods mainly perform continual training to mitigate such a misalignment. While effective to some extent but is far from being addressed on both the language modeling and downstream tasks. In this paper, we empirically observe that temporal generalization is closely affiliated with lexical semantic change, which is one of the essential phenomena of natural languages. Based on this observation, we propose a simple yet effective lexical-level masking strategy to post-train a converged language model. Experiments on two pre-trained language models, two different classification tasks, and four benchmark datasets demonstrate the effectiveness of our proposed method over existing temporal adaptation methods, i.e., continual training with new data. Our code is available at https://github.com/zhaochen0110/LMLM.

pdf bib
Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling
Zhijun Wang | Xuebo Liu | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Existing research generally treats Chinese character as a minimum unit for representation. However, such Chinese character representation will suffer two bottlenecks: 1) Learning bottleneck, the learning cannot benefit from its rich internal features (e.g., radicals and strokes); and 2) Parameter bottleneck, each individual character has to be represented by a unique vector. In this paper, we introduce a novel representation method for Chinese characters to break the bottlenecks, namely StrokeNet, which represents a Chinese character by a Latinized stroke sequence (e.g., “凹 (concave)” to “ajaie” and “凸 (convex)” to “aeaqe”). Specifically, StrokeNet maps each stroke to a specific Latin character, thus allowing similar Chinese characters to have similar Latin representations. With the introduction of StrokeNet to neural machine translation (NMT), many powerful but not applicable techniques to non-Latin languages (e.g., shared subword vocabulary learning and ciphertext-based data augmentation) can now be perfectly implemented. Experiments on the widely-used NIST Chinese-English, WMT17 Chinese-English and IWSLT17 Japanese-English NMT tasks show that StrokeNet can provide a significant performance boost over the strong baselines with fewer model parameters, achieving 26.5 BLEU on the WMT17 Chinese-English task which is better than any previously reported results without using monolingual data. Code and scripts are freely available at https://github.com/zjwang21/StrokeNet.

pdf bib
Revisiting Grammatical Error Correction Evaluation and Beyond
Peiyuan Gong | Xuebo Liu | Heyan Huang | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Pretraining-based (PT-based) automatic evaluation metrics (e.g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e.g., machine translation and text summarization) due to their better correlation with human judgments over traditional overlap-based methods. Although PT-based methods have become the de facto standard for training grammatical error correction (GEC) systems, GEC evaluation still does not benefit from pretrained knowledge. This paper takes the first step towards understanding and improving GEC evaluation with pretraining. We first find that arbitrarily applying PT-based metrics to GEC evaluation brings unsatisfactory correlation results because of the excessive attention to inessential systems outputs (e.g., unchanged parts). To alleviate the limitation, we propose a novel GEC evaluation metric to achieve the best of both worlds, namely PT-M2 which only uses PT-based metrics to score those corrected parts. Experimental results on the CoNLL14 evaluation task show that PT-M2 significantly outperforms existing methods, achieving a new state-of-the-art result of 0.949 Pearson correlation. Further analysis reveals that PT-M2 is robust to evaluate competitive GEC systems. Source code and scripts are freely available at https://github.com/pygongnlp/PT-M2.

pdf bib
WR-One2Set: Towards Well-Calibrated Keyphrase Generation
Binbin Xie | Xiangpeng Wei | Baosong Yang | Huan Lin | Jun Xie | Xiaoli Wang | Min Zhang | Jinsong Su
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Keyphrase generation aims to automatically generate short phrases summarizing an input document. The recently emerged ONE2SET paradigm (Ye et al., 2021) generates keyphrases as a set and has achieved competitive performance. Nevertheless, we observe serious calibration errors outputted by ONE2SET, especially in the over-estimation of ∅ token (means “no corresponding keyphrase”). In this paper, we deeply analyze this limitation and identify two main reasons behind: 1) the parallel generation has to introduce excessive ∅ as padding tokens into training instances; and 2) the training mechanism assigning target to each slot is unstable and further aggravates the ∅ token over-estimation. To make the model well-calibrated, we propose WR-ONE2SET which extends ONE2SET with an adaptive instance-level cost Weighting strategy and a target Re-assignment mechanism. The former dynamically penalizes the over-estimated slots for different instances thus smoothing the uneven training distribution. The latter refines the original inappropriate assignment and reduces the supervisory signals of over-estimated slots. Experimental results on commonly-used datasets demonstrate the effectiveness and generality of our proposed paradigm.

pdf bib
Extending Phrase Grounding with Pronouns in Visual Dialogues
Panzhong Lu | Xin Zhang | Meishan Zhang | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Conventional phrase grounding aims to localize noun phrases mentioned in a given caption to their corresponding image regions, which has achieved great success recently. Apparently, sole noun phrase grounding is not enough for cross-modal visual language understanding. Here we extend the task by considering pronouns as well. First, we construct a dataset of phrase grounding with both noun phrases and pronouns to image regions. Based on the dataset, we test the performance of phrase grounding by using a state-of-the-art literature model of this line. Then, we enhance the baseline grounding model with coreference information which should help our task potentially, modeling the coreference structures with graph convolutional networks. Experiments on our dataset, interestingly, show that pronouns are easier to ground than noun phrases, where the possible reason might be that these pronouns are much less ambiguous. Additionally, our final model with coreference information can significantly boost the grounding performance of both noun phrases and pronouns.

pdf bib
JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation
Xiaobo Liang | Lijun Wu | Juntao Li | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Transformer-based autoregressive and non-autoregressive models have played an essential role in sequence generation tasks. The autoregressive model can obtain excellent performance, while the non-autoregressive model brings fast decoding speed for inference. In this paper, we propose JANUS, a Joint Autoregressive and Non-autoregressive training method using aUxiliary losS to enhance the model performance in both AR and NAR manner simultaneously and effectively alleviate the problem of distribution discrepancy.Further, we pre-train BART with JANUS on a large corpus with minimal cost (16 GPU days) and make the BART-JANUS capable of non-autoregressive generation, demonstrating that our approach can transfer the AR knowledge to NAR. Empirically, we show our approach and BART-JANUS can achieve significant improvement on multiple generation tasks, including machine translation and GLGE benchmarks. Our code is available at Github.

pdf bib
ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation
Zhaocong Li | Xuebo Liu | Derek F. Wong | Lidia S. Chao | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Transfer learning is a simple and powerful method that can be used to boost model performance of low-resource neural machine translation (NMT). Existing transfer learning methods for NMT are static, which simply transfer knowledge from a parent model to a child model once via parameter initialization. In this paper, we propose a novel transfer learning method for NMT, namely ConsistTL, which can continuously transfer knowledge from the parent model during the training of the child model. Specifically, for each training instance of the child model, ConsistTL constructs the semantically-equivalent instance for the parent model and encourages prediction consistency between the parent and child for this instance, which is equivalent to the child model learning each instance under the guidance of the parent model. Experimental results on five low-resource NMT tasks demonstrate that ConsistTL results in significant improvements over strong transfer learning baselines, with a gain up to 1.7 BLEU over the existing back-translation model on the widely-used WMT17 Turkish-English benchmark. Further analysis reveals that ConsistTL can improve the inference calibration of the child model. Code and scripts are freely available at https://github.com/NLP2CT/ConsistTL.

pdf bib
Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
Yiming Zhang | Min Zhang | Sai Wu | Junbo Zhao
Findings of the Association for Computational Linguistics: ACL 2022

The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence. The development of the ABSA task is very much hindered by the lack of annotated data. To tackle this, the prior works have studied the possibility of utilizing the sentiment analysis (SA) datasets to assist in training the ABSA model, primarily via pretraining or multi-task learning. In this article, we follow this line, and for the first time, we manage to apply the Pseudo-Label (PL) method to merge the two homogeneous tasks. While it seems straightforward to use generated pseudo labels to handle this case of label granularity unification for two highly related tasks, we identify its major challenge in this paper and propose a novel framework, dubbed as Dual-granularity Pseudo Labeling (DPL). Further, similar to PL, we regard the DPL as a general framework capable of combining other prior methods in the literature. Through extensive experiments, DPL has achieved state-of-the-art performance on standard benchmarks surpassing the prior work significantly.

pdf bib
Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference
Yuxia Wang | Minghan Wang | Yimeng Chen | Shimin Tao | Jiaxin Guo | Chang Su | Min Zhang | Hao Yang
Findings of the Association for Computational Linguistics: ACL 2022

Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity. Several recent efforts have been made to acknowledge and embrace the existence of ambiguity, and explore how to capture the human disagreement distribution. In contrast with directly learning from gold ambiguity labels, relying on special resource, we argue that the model has naturally captured the human ambiguity distribution as long as it’s calibrated, i.e. the predictive probability can reflect the true correctness likelihood. Our experiments show that when model is well-calibrated, either by label smoothing or temperature scaling, it can obtain competitive performance as prior work, on both divergence scores between predictive probability and the true human opinion distribution, and the accuracy. This reveals the overhead of collecting gold ambiguity labels can be cut, by broadly solving how to calibrate the NLI network.

pdf bib
Synchronous Refinement for Neural Machine Translation
Kehai Chen | Masao Utiyama | Eiichiro Sumita | Rui Wang | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2022

Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner. However, the auto-regressive decoder faces a deep-rooted one-pass issue whereby each generated word is considered as one element of the final output regardless of whether it is correct or not. These generated wrong words further constitute the target historical context to affect the generation of subsequent target words. This paper proposes a novel synchronous refinement method to revise potential errors in the generated words by considering part of the target future context. Particularly, the proposed approach allows the auto-regressive decoder to refine the previously generated target words and generate the next target word synchronously. The experimental results on three widely-used machine translation tasks demonstrated the effectiveness of the proposed approach.

pdf bib
Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging
Houquan Zhou | Yang Li | Zhenghua Li | Min Zhang
Findings of the Association for Computational Linguistics: ACL 2022

In recent years, large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks. But, in the unsupervised POS tagging task, works utilizing PLMs are few and fail to achieve state-of-the-art (SOTA) performance. The recent SOTA performance is yielded by a Guassian HMM variant proposed by He et al. (2018). However, as a generative model, HMM makes very strong independence assumptions, making it very challenging to incorporate contexualized word representations from PLMs. In this work, we for the first time propose a neural conditional random field autoencoder (CRF-AE) model for unsupervised POS tagging. The discriminative encoder of CRF-AE can straightforwardly incorporate ELMo word representations. Moreover, inspired by feature-rich HMM, we reintroduce hand-crafted features into the decoder of CRF-AE. Finally, experiments clearly show that our model outperforms previous state-of-the-art models by a large margin on Penn Treebank and multilingual Universal Dependencies treebank v2.0.

pdf bib
Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation
Huan Lin | Baosong Yang | Liang Yao | Dayiheng Liu | Haibo Zhang | Jun Xie | Min Zhang | Jinsong Su
Findings of the Association for Computational Linguistics: NAACL 2022

Diverse NMT aims at generating multiple diverse yet faithful translations given a source sentence. In this paper, we investigate a common shortcoming in existing diverse NMT studies: the model is usually trained with single reference, while expected to generate multiple candidate translations in inference. The discrepancy between training and inference enlarges the confidence variance and quality gap among candidate translations and thus hinders model performance. To deal with this defect, we propose a multi-candidate optimization framework for diverse NMT. Specifically, we define assessments to score the diversity and the quality of candidate translations during training, and optimize the diverse NMT model with two strategies based on reinforcement learning, namely hard constrained training and soft constrained training. We conduct experiments on NIST Chinese-English and WMT14 English-German translation tasks. The results illustrate that our framework is transparent to basic diverse NMT models, and universally makes better trade-off between diversity and quality. Our source codeis available at https://github.com/DeepLearnXMU/MultiCanOptim.

pdf bib
Part Represents Whole: Improving the Evaluation of Machine Translation System Using Entropy Enhanced Metrics
Yilun Liu | Shimin Tao | Chang Su | Min Zhang | Yanqing Zhao | Hao Yang
Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022

Machine translation (MT) metrics often experience poor correlations with human assessments. In terms of MT system evaluation, most metrics pay equal attentions to every sample in an evaluation set, while in human evaluation, difficult sentences often make candidate systems distinguishable via notable fluctuations in human scores, especially when systems are competitive. We find that samples with high entropy values, which though usually count less than 5%, tend to play a key role in MT evaluation: when the evaluation set is shrunk to only the high-entropy portion, correlations with human assessments are actually improved. Thus, in this paper, we propose a fast and unsupervised approach to enhance MT metrics using entropy, expanding the dimension of evaluation by introducing sentence-level difficulty. A translation hypothesis with a significantly high entropy value is considered difficult and receives a large weight in aggregation of system-level scores. Experimental results on five sub-tracks in the WMT19 Metrics shared tasks show that our proposed method significantly enhanced the performance of commonly-used MT metrics in terms of system-level correlations with human assessments, even outperforming existing SOTA metrics. In particular, all enhanced metrics exhibit overall stability in correlations with human assessments in circumstances where only competitive MT systems are included, while the corresponding vanilla metrics fail to correlate with human assessments.

pdf bib
Third-Party Aligner for Neural Word Alignments
Jinpeng Zhang | Chuanqi Dong | Xiangyu Duan | Yuqi Zhang | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2022

Word alignment is to find translationally equivalent words between source and target sentences. Previous work has demonstrated that self-training can achieve competitive word alignment results. In this paper, we propose to use word alignments generated by a third-party word aligner to supervise the neural word alignment training. Specifically, source word and target word of each word pair aligned by the third-party aligner are trained to be close neighbors to each other in the contextualized embedding space when fine-tuning a pre-trained cross-lingual language model. Experiments on the benchmarks of various language pairs show that our approach can surprisingly do self-correction over the third-party supervision by finding more accurate word alignments and deleting wrong word alignments, leading to better performance than various third-party word aligners, including the currently best one. When we integrate all supervisions from various third-party aligners, we achieve state-of-the-art word alignment performances, with averagely more than two points lower alignment error rates than the best third-party aligner.We released our code at https://github.com/sdongchuanqi/Third-Party-Supervised-Aligner.

pdf bib
Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning
Hongqiu Wu | Ruixue Ding | Hai Zhao | Boli Chen | Pengjun Xie | Fei Huang | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2022

Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios. However, learning multiple training objectives in a single model is challenging due to the unknown relative significance as well as the potential contrariety between them. Empirical studies have shown that the current objective sampling in an ad-hoc manual setting makes the learned language representation barely converge to the desired optimum. Thus, we propose MOMETAS, a novel adaptive sampler based on meta-learning, which learns the latent sampling pattern on arbitrary pre-training objectives. Such a design is lightweight with negligible additional training overhead. To validate our approach, we adopt five objectives and conduct continual pre-training with BERT-base and BERT-large models, where MOMETAS demonstrates universal performance gain over other rule-based sampling strategies on 14 natural language processing tasks.

pdf bib
Diformer: Directional Transformer for Neural Machine Translation
Minghan Wang | Jiaxin Guo | Yuxia Wang | Daimeng Wei | Hengchao Shang | Yinglu Li | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang
Proceedings of the 23rd Annual Conference of the European Association for Machine Translation

Autoregressive (AR) and Non-autoregressive (NAR) models have their own superiority on the performance and latency, combining them into one model may take advantage of both. Current combination frameworks focus more on the integration of multiple decoding paradigms with a unified generative model, e.g. Masked Language Model. However, the generalization can be harmful on the performance due to the gap between training objective and inference. In this paper, we aim to close the gap by preserving the original objective of AR and NAR under a unified framework. Specifically, we propose the Directional Transformer (Diformer) by jointly modelling AR and NAR into three generation directions (left-to-right, right-to-left and straight) with a newly introduced direction variable, which works by controlling the prediction of each token to have specific dependencies under that direction. The unification achieved by direction successfully preserves the original dependency assumption used in AR and NAR, retaining both generalization and performance. Experiments on 4 WMT benchmarks demonstrate that Diformer outperforms current united-modelling works with more than 1.5 BLEU points for both AR and NAR decoding, and is also competitive to the state-of-the-art independent AR and NAR models.

pdf bib
HW-TSC at SemEval-2022 Task 3: A Unified Approach Fine-tuned on Multilingual Pretrained Model for PreTENS
Yinglu Li | Min Zhang | Xiaosong Qiao | Minghan Wang
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

In the paper, we describe a unified system for task 3 of SemEval-2022. The task aims to recognize the semantic structures of sentences by providing two nominal arguments and to evaluate the degree of taxonomic relations. We utilise the strategy that adding language prefix tag in the training set, which is effective for the model. We split the training set to avoid the translation information to be learnt by the model. For the task, we propose a unified model fine-tuned on the multilingual pretrained model, XLM-RoBERTa. The model performs well in subtask 1 (the binary classification subtask). In order to verify whether our model could also perform better in subtask 2 (the regression subtask), the ranking score is transformed into classification labels by an up-sampling strategy. With the ensemble strategy, the performance of our model can be also improved. As a result, the model obtained the second place for subtask 1 and subtask 2 in the competition evaluation.

pdf bib
HW-TSC at SemEval-2022 Task 7: Ensemble Model Based on Pretrained Models for Identifying Plausible Clarifications
Xiaosong Qiao | Yinglu Li | Min Zhang | Minghan Wang | Hao Yang | Shimin Tao | Qin Ying
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper describes the system for the identifying Plausible Clarifications of Implicit and Underspecified Phrases. This task was set up as an English cloze task, in which clarifications are presented as possible fillers and systems have to score how well each filler plausibly fits in a given context. For this shared task, we propose our own solutions, including supervised proaches, unsupervised approaches with pretrained models, and then we use these models to build an ensemble model. Finally we get the 2nd best result in the subtask1 which is a classification task, and the 3rd best result in the subtask2 which is a regression task.

pdf bib
Partial Could Be Better than Whole. HW-TSC 2022 Submission for the Metrics Shared Task
Yilun Liu | Xiaosong Qiao | Zhanglin Wu | Su Chang | Min Zhang | Yanqing Zhao | Song Peng | Shimin Tao | Hao Yang | Ying Qin | Jiaxin Guo | Minghan Wang | Yinglu Li | Peng Li | Xiaofeng Zhao
Proceedings of the Seventh Conference on Machine Translation (WMT)

In this paper, we present the contribution of HW-TSC to WMT 2022 Metrics Shared Task. We propose one reference-based metric, HWTSC-EE-BERTScore*, and four referencefree metrics including HWTSC-Teacher-Sim, HWTSC-TLM, KG-BERTScore and CROSSQE. Among these metrics, HWTSC-Teacher-Sim and CROSS-QE are supervised, whereas HWTSC-EE-BERTScore*, HWTSC-TLM and KG-BERTScore are unsupervised. We use these metrics in the segment-level and systemlevel tracks. Overall, our systems achieve strong results for all language pairs on previous test sets and a new state-of-the-art in many sys-level case sets.

pdf bib
CrossQE: HW-TSC 2022 Submission for the Quality Estimation Shared Task
Shimin Tao | Su Chang | Ma Miaomiao | Hao Yang | Xiang Geng | Shujian Huang | Min Zhang | Jiaxin Guo | Minghan Wang | Yinglu Li
Proceedings of the Seventh Conference on Machine Translation (WMT)

Quality estimation (QE) is a crucial method to investigate automatic methods for estimating the quality of machine translation results without reference translations. This paper presents Huawei Translation Services Center’s (HW-TSC’s) work called CrossQE in WMT 2022 QE shared tasks 1 and 2, namely sentence- and word- level quality prediction and explainable QE.CrossQE employes the framework of predictor-estimator for task 1, concretely with a pre-trained cross-lingual XLM-RoBERTa large as predictor and task-specific classifier or regressor as estimator. An extensive set of experimental results show that after adding bottleneck adapter layer, mean teacher loss, masked language modeling task loss and MC dropout methods in CrossQE, the performance has improved to a certain extent. For task 2, CrossQE calculated the cosine similarity between each word feature in the target and each word feature in the source by task 1 sentence-level QE system’s predictor, and used the inverse value of maximum similarity between each word in the target and the source as the word translation error risk value. Moreover, CrossQE has outstanding performance on QE test sets of WMT 2022.

pdf bib
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation
Yinglu Li | Minghan Wang | Jiaxin Guo | Xiaosong Qiao | Yuxia Wang | Daimeng Wei | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang | Ying Qin
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

This paper describes the HW-TSC’s designation of the Offline Speech Translation System submitted for IWSLT 2022 Evaluation. We explored both cascade and end-to-end system on three language tracks (en-de, en-zh and en-ja), and we chose the cascade one as our primary submission. For the automatic speech recognition (ASR) model of cascade system, there are three ASR models including Conformer, S2T-Transformer and U2 trained on the mixture of five datasets. During inference, transcripts are generated with the help of domain controlled generation strategy. Context-aware reranking and ensemble based anti-interference strategy are proposed to produce better ASR outputs. For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora. Our cascade system shows competitive performance than the known offline systems in the industry and academia.

pdf bib
The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation
Minghan Wang | Jiaxin Guo | Yinglu Li | Xiaosong Qiao | Yuxia Wang | Zongyao Li | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang | Ying Qin
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

This paper presents our work in the participation of IWSLT 2022 simultaneous speech translation evaluation. For the track of text-to-text (T2T), we participate in three language pairs and build wait-k based simultaneous MT (SimulMT) model for the task. The model was pretrained on WMT21 news corpora, and was further improved with in-domain fine-tuning and self-training. For the speech-to-text (S2T) track, we designed both cascade and end-to-end form in three language pairs. The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track. The end-to-end system is a simultaneous speech translation (SimulST) model based on wait-k strategy, which is directly trained on a synthetic corpus produced by translating all texts of ASR corpora into specific target language with an offline MT model. It also contains a heuristic sentence breaking strategy, preventing it from finishing the translation before the the end of the speech. We evaluate our systems on the MUST-C tst-COMMON dataset and show that the end-to-end system is competitive to the cascade one. Meanwhile, we also demonstrate that the SimulMT model can be efficiently optimized by these approaches, resulting in the improvements of 1-2 BLEU points.

pdf bib
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
Jiaxin Guo | Yinglu Li | Minghan Wang | Xiaosong Qiao | Yuxia Wang | Hengchao Shang | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang | Ying Qin
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022. We design a cascade system consisted of an ASR model, machine translation model and TTS model to convert the speech from one language into another language(en-de). For the ASR part, we find that better performance can be obtained by ensembling multiple heterogeneous ASR models and performing reranking on beam candidates. And we find that the combination of context-aware reranking strategy and MT model fine-tuned on the in-domain dataset is helpful to improve the performance. Because it can mitigate the problem that the inconsistency in transcripts caused by the lack of context. Finally, we use VITS model provided officially to reproduce audio files from the translation hypothesis.

pdf bib
SelfMix: Robust Learning against Textual Label Noise with Self-Mixup Training
Dan Qiao | Chenchen Dai | Yuyang Ding | Juntao Li | Qiang Chen | Wenliang Chen | Min Zhang
Proceedings of the 29th International Conference on Computational Linguistics

The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise inevitably exists in training data, damaging the effectiveness, robustness, and generalization of the models constructed on such data. Recently, remarkable achievements have been made to mitigate this dilemma in visual data, while only a few explore textual data. To fill this gap, we present SelfMix, a simple yet effective method, to handle label noise in text classification tasks. SelfMix uses the Gaussian Mixture Model to separate samples and leverages semi-supervised learning. Unlike previous works requiring multiple models, our method utilizes the dropout mechanism on a single model to reduce the confirmation bias in self-training and introduces a textual level mixup training strategy. Experimental results on three text classification benchmarks with different types of text show that the performance of our proposed method outperforms these strong baselines designed for both textual and visual data under different noise ratios and noise types. Our anonymous code is available at https://github.com/noise-learning/SelfMix.

pdf bib
Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing
Shilin Zhou | Qingrong Xia | Zhenghua Li | Yu Zhang | Yu Hong | Min Zhang
Proceedings of the 29th International Conference on Computational Linguistics

This paper proposes to cast end-to-end span-based SRL as a word-based graph parsing task. The major challenge is how to represent spans at the word level. Borrowing ideas from research on Chinese word segmentation and named entity recognition, we propose and compare four different schemata of graph representation, i.e., BES, BE, BIES, and BII, among which we find that the BES schema performs the best. We further gain interesting insights through detailed analysis. Moreover, we propose a simple constrained Viterbi procedure to ensure the legality of the output graph according to the constraints of the SRL structure. We conduct experiments on two widely used benchmark datasets, i.e., CoNLL05 and CoNLL12. Results show that our word-based graph parsing approach achieves consistently better performance than previous results, under all settings of end-to-end and predicate-given, without and with pre-trained language models (PLMs). More importantly, our model can parse 669/252 sentences per second, without and with PLMs respectively.

pdf bib
Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments
Yu Zhang | Qingrong Xia | Shilin Zhou | Yong Jiang | Guohong Fu | Min Zhang
Proceedings of the 29th International Conference on Computational Linguistics

Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community. Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based. Despite ubiquity, they share some intrinsic drawbacks of not considering internal argument structures, potentially hindering the model’s expressiveness. The key challenge is arguments are flat structures, and there are no determined subtree realizations for words inside arguments. To remedy this, in this paper, we propose to regard flat argument spans as latent subtrees, accordingly reducing SRL to a tree parsing task. In particular, we equip our formulation with a novel span-constrained TreeCRF to make tree structures span-aware and further extend it to the second-order case. We conduct extensive experiments on CoNLL05 and CoNLL12 benchmarks. Results reveal that our methods perform favorably better than all previous syntax-agnostic works, achieving new state-of-the-art under both end-to-end and w/ gold predicates settings.

pdf bib
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training
Zhongjian Miao | Xiang Li | Liyan Kang | Wen Zhang | Chulun Zhou | Yidong Chen | Bin Wang | Min Zhang | Jinsong Su
Proceedings of the 29th International Conference on Computational Linguistics

Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples. They require the model to translate both the authentic source sentence and its adversarial counterpart into the identical target sentence within the same training stage, which may be a suboptimal choice to achieve robust NMT. In this paper, we first conduct a preliminary study to confirm this claim and further propose an Iterative Scheduled Data-switch Training Framework to mitigate this problem. Specifically, we introduce two training stages, iteratively switching between authentic and adversarial examples. Compared with previous studies, our model focuses more on just one type of examples at each single stage, which can better exploit authentic and adversarial examples, and thus obtaining a better robust NMT model. Moreover, we introduce an improved curriculum learning method with a sampling strategy to better schedule the process of noise injection. Experimental results show that our model significantly surpasses several competitive baselines on four translation benchmarks. Our source code is available at https://github.com/DeepLearnXMU/RobustNMT-ISDST.

pdf bib
Speaker-Aware Discourse Parsing on Multi-Party Dialogues
Nan Yu | Guohong Fu | Min Zhang
Proceedings of the 29th International Conference on Computational Linguistics

Discourse parsing on multi-party dialogues is an important but difficult task in dialogue systems and conversational analysis. It is believed that speaker interactions are helpful for this task. However, most previous research ignores speaker interactions between different speakers. To this end, we present a speaker-aware model for this task. Concretely, we propose a speaker-context interaction joint encoding (SCIJE) approach, using the interaction features between different speakers. In addition, we propose a second-stage pre-training task, same speaker prediction (SSP), enhancing the conversational context representations by predicting whether two utterances are from the same speaker. Experiments on two standard benchmark datasets show that the proposed model achieves the best-reported performance in the literature. We will release the codes of this paper to facilitate future research.

pdf bib
Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis
Zijie Lin | Bin Liang | Yunfei Long | Yixue Dang | Min Yang | Min Zhang | Ruifeng Xu
Proceedings of the 29th International Conference on Computational Linguistics

The existing research efforts in Multimodal Sentiment Analysis (MSA) have focused on developing the expressive ability of neural networks to fuse information from different modalities. However, these approaches lack a mechanism to understand the complex relations within and across different modalities, since some sentiments may be scattered in different modalities. To this end, in this paper, we propose a novel hierarchical graph contrastive learning (HGraph-CL) framework for MSA, aiming to explore the intricate relations of intra- and inter-modal representations for sentiment extraction. Specifically, regarding the intra-modal level, we build a unimodal graph for each modality representation to account for the modality-specific sentiment implications. Based on it, a graph contrastive learning strategy is adopted to explore the potential relations based on unimodal graph augmentations. Furthermore, we construct a multimodal graph of each instance based on the unimodal graphs to grasp the sentiment relations between different modalities. Then, in light of the multimodal augmentation graphs, a graph contrastive learning strategy over the inter-modal level is proposed to ulteriorly seek the possible graph structures for precisely learning sentiment relations. This essentially allows the framework to understand the appropriate graph structures for learning intricate relations among different modalities. Experimental results on two benchmark datasets show that the proposed framework outperforms the state-of-the-art baselines in MSA.

2021

pdf bib
XLPT-AMR: Cross-Lingual Pre-Training via Multi-Task Learning for Zero-Shot AMR Parsing and Text Generation
Dongqin Xu | Junhui Li | Muhua Zhu | Min Zhang | Guodong Zhou
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Due to the scarcity of annotated data, Abstract Meaning Representation (AMR) research is relatively limited and challenging for languages other than English. Upon the availability of English AMR dataset and English-to- X parallel datasets, in this paper we propose a novel cross-lingual pre-training approach via multi-task learning (MTL) for both zeroshot AMR parsing and AMR-to-text generation. Specifically, we consider three types of relevant tasks, including AMR parsing, AMR-to-text generation, and machine translation. We hope that knowledge gained while learning for English AMR parsing and text generation can be transferred to the counterparts of other languages. With properly pretrained models, we explore four different finetuning methods, i.e., vanilla fine-tuning with a single task, one-for-all MTL fine-tuning, targeted MTL fine-tuning, and teacher-studentbased MTL fine-tuning. Experimental results on AMR parsing and text generation of multiple non-English languages demonstrate that our approach significantly outperforms a strong baseline of pre-training approach, and greatly advances the state of the art. In detail, on LDC2020T07 we have achieved 70.45%, 71.76%, and 70.80% in Smatch F1 for AMR parsing of German, Spanish, and Italian, respectively, while for AMR-to-text generation of the languages, we have obtained 25.69, 31.36, and 28.42 in BLEU respectively. We make our code available on github https://github.com/xdqkid/XLPT-AMR.

pdf bib
LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding
Yang Xu | Yiheng Xu | Tengchao Lv | Lei Cui | Furu Wei | Guoxin Wang | Yijuan Lu | Dinei Florencio | Cha Zhang | Wanxiang Che | Min Zhang | Lidong Zhou
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make it better capture the cross-modality interaction in the pre-training stage. Meanwhile, it also integrates a spatial-aware self-attention mechanism into the Transformer architecture so that the model can fully understand the relative positional relationship among different text blocks. Experiment results show that LayoutLMv2 outperforms LayoutLM by a large margin and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including FUNSD (0.7895 to 0.8420), CORD (0.9493 to 0.9601), SROIE (0.9524 to 0.9781), Kleister-NDA (0.8340 to 0.8520), RVL-CDIP (0.9443 to 0.9564), and DocVQA (0.7295 to 0.8672).

pdf bib
An In-depth Study on Internal Structure of Chinese Words
Chen Gong | Saihao Huang | Houquan Zhou | Zhenghua Li | Min Zhang | Zhefeng Wang | Baoxing Huai | Nicholas Jing Yuan
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Unlike English letters, Chinese characters have rich and specific meanings. Usually, the meaning of a word can be derived from its constituent characters in some way. Several previous works on syntactic parsing propose to annotate shallow word-internal structures for better utilizing character-level information. This work proposes to model the deep internal structures of Chinese words as dependency trees with 11 labels for distinguishing syntactic relationships. First, based on newly compiled annotation guidelines, we manually annotate a word-internal structure treebank (WIST) consisting of over 30K multi-char words from Chinese Penn Treebank. To guarantee quality, each word is independently annotated by two annotators and inconsistencies are handled by a third senior annotator. Second, we present detailed and interesting analysis on WIST to reveal insights on Chinese word formation. Third, we propose word-internal structure parsing as a new task, and conduct benchmark experiments using a competitive dependency parser. Finally, we present two simple ways to encode word-internal structures, leading to promising gains on the sentence-level syntactic parsing task.

pdf bib
Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation
Xin Liu | Baosong Yang | Dayiheng Liu | Haibo Zhang | Weihua Luo | Min Zhang | Haiying Zhang | Jinsong Su
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary. This potentially weakens the effect when applying pretrained models into natural language generation (NLG) tasks, especially for the subword distributions between upstream and downstream tasks with significant discrepancy. Towards approaching this problem, we extend the vanilla pretrain-finetune pipeline with an extra embedding transfer step. Specifically, a plug-and-play embedding generator is introduced to produce the representation of any input token, according to pre-trained embeddings of its morphologically similar ones. Thus, embeddings of mismatch tokens in downstream tasks can also be efficiently initialized. We conduct experiments on a variety of NLG tasks under the pretrain-finetune fashion. Experimental results and extensive analyses show that the proposed strategy offers us opportunities to feel free to transfer the vocabulary, leading to more efficient and better performed downstream NLG models.

pdf bib
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts
David Chiang | Min Zhang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts

pdf bib
Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation
Minghan Wang | Jiaxin Guo | Yimeng Chen | Chang Su | Min Zhang | Shimin Tao | Hao Yang
Proceedings of Machine Translation Summit XVIII: Research Track

Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT. To this end and we propose a transfer learning solution. Specifically and 1) A vanilla Transformer is pre-trained on massive bilingual text-only corpus to obtain prior knowledge; 2) A multimodal Transformer named VLTransformer is proposed with several components incorporated visual contexts; and 3) The parameters of VLTransformer are initialized with the pre-trained vanilla Transformer and then being fine-tuned on MMT tasks with a newly proposed method named cross-modal masking which forces the model to learn from both modalities. We evaluated on the Multi30k en-de and en-fr dataset and improving up to 8% BLEU score compared with the SOTA performance. The experimental result demonstrates that performing transfer learning with monomodal pre-trained NMT model on multimodal NMT tasks can obtain considerable boosts.

pdf bib
A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents
Qingrong Xia | Bo Zhang | Rui Wang | Zhenghua Li | Yue Zhang | Fei Huang | Luo Si | Min Zhang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of “Who expressed what opinions towards what” in one sentence. In this work, motivated by its span-based representations of opinion expressions and roles, we propose a unified span-based approach for the end-to-end OM setting. Furthermore, inspired by the unified span-based formalism of OM and constituent parsing, we explore two different methods (multi-task learning and graph convolutional neural network) to integrate syntactic constituents into the proposed model to help OM. We conduct experiments on the commonly used MPQA 2.0 dataset. The experimental results show that our proposed unified span-based approach achieves significant improvements over previous works in the exact F1 score and reduces the number of wrongly-predicted opinion expressions and roles, showing the effectiveness of our method. In addition, incorporating the syntactic constituents achieves promising improvements over the strong baseline enhanced by contextualized word representations.

pdf bib
A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing
Yang Hou | Houquan Zhou | Zhenghua Li | Yu Zhang | Min Zhang | Zhefeng Wang | Baoxing Huai | Nicholas Jing Yuan
Proceedings of the 25th Conference on Computational Natural Language Learning

The most straightforward approach to joint word segmentation (WS), part-of-speech (POS) tagging, and constituent parsing is converting a word-level tree into a char-level tree, which, however, leads to two severe challenges. First, a larger label set (e.g., ≥ 600) and longer inputs both increase computational costs. Second, it is difficult to rule out illegal trees containing conflicting production rules, which is important for reliable model evaluation. If a POS tag (like VV) is above a phrase tag (like VP) in the output tree, it becomes quite complex to decide word boundaries. To deal with both challenges, this work proposes a two-stage coarse-to-fine labeling framework for joint WS-POS-PAR. In the coarse labeling stage, the joint model outputs a bracketed tree, in which each node corresponds to one of four labels (i.e., phrase, subphrase, word, subword). The tree is guaranteed to be legal via constrained CKY decoding. In the fine labeling stage, the model expands each coarse label into a final label (such as VP, VP*, VV, VV*). Experiments on Chinese Penn Treebank 5.1 and 7.0 show that our joint model consistently outperforms the pipeline approach on both settings of w/o and w/ BERT, and achieves new state-of-the-art performance.

pdf bib
数据标注方法比较研究:以依存句法树标注为例(Comparison Study on Data Annotation Approaches: Dependency Tree Annotation as Case Study)
Mingyue Zhou (周明月) | Chen Gong (龚晨) | Zhenghua Li (李正华) | Min Zhang (张民)
Proceedings of the 20th Chinese National Conference on Computational Linguistics

数据标注最重要的考虑因素是数据的质量和标注代价。我们调研发现自然语言处理领域的数据标注工作通常采用机标人校的标注方法以降低代价;同时,很少有工作严格对比不同标注方法,以探讨标注方法对标注质量和代价的影响。该文借助一个成熟的标注团队,以依存句法数据标注为案例,实验对比了机标人校、双人独立标注、及本文通过融合前两种方法所新提出的人机独立标注方法,得到了一些初步的结论。

pdf bib
How Length Prediction Influence the Performance of Non-Autoregressive Translation?
Minghan Wang | Guo Jiaxin | Yuxia Wang | Yimeng Chen | Su Chang | Hengchao Shang | Min Zhang | Shimin Tao | Hao Yang
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Length prediction is a special task in a series of NAT models where target length has to be determined before generation. However, the performance of length prediction and its influence on translation quality has seldom been discussed. In this paper, we present comprehensive analyses on length prediction task of NAT, aiming to find the factors that influence performance, as well as how it associates with translation quality. We mainly perform experiments based on Conditional Masked Language Model (CMLM) (Ghazvininejad et al., 2019), a representative NAT model, and evaluate it on two language pairs, En-De and En-Ro. We draw two conclusions: 1) The performance of length prediction is mainly influenced by properties of language pairs such as alignment pattern, word order or intrinsic length ratio, and is also affected by the usage of knowledge distilled data. 2) There is a positive correlation between the performance of the length prediction and the BLEU score.

pdf bib
HI-CMLM: Improve CMLM with Hybrid Decoder Input
Minghan Wang | Guo Jiaxin | Yuxia Wang | Yimeng Chen | Su Chang | Daimeng Wei | Min Zhang | Shimin Tao | Hao Yang
Proceedings of the 14th International Conference on Natural Language Generation

Mask-predict CMLM (Ghazvininejad et al.,2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence. In this work, we mitigate this problem by combining copied source with embeddings of [MASK] in decoder. Notably. it’s not a straightforward copying that is shown to be useless, but a novel heuristic hybrid strategy — fence-mask. Experimental results show that it gains consistent boosts on both WMT14 En<->De and WMT16 En<->Ro corpus by 0.5 BLEU on average, and 1 BLEU for less-informative short sentences. This reveals that incorporating additional information by proper strategies is beneficial to improve CMLM, particularly translation quality of short texts and speeding up early-stage convergence.

pdf bib
HW-TSC’s Participation in the WMT 2021 News Translation Shared Task
Daimeng Wei | Zongyao Li | Zhanglin Wu | Zhengzhe Yu | Xiaoyu Chen | Hengchao Shang | Jiaxin Guo | Minghan Wang | Lizhi Lei | Min Zhang | Hao Yang | Ying Qin
Proceedings of the Sixth Conference on Machine Translation

This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task. We participate in 7 language pairs, including Zh/En, De/En, Ja/En, Ha/En, Is/En, Hi/Bn, and Xh/Zu in both directions under the constrained condition. We use Transformer architecture and obtain the best performance via multiple variants with larger parameter sizes. We perform detailed pre-processing and filtering on the provided large-scale bilingual and monolingual datasets. Several commonly used strategies are used to train our models, such as Back Translation, Forward Translation, Multilingual Translation, Ensemble Knowledge Distillation, etc. Our submission obtains competitive results in the final evaluation.

pdf bib
HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task
Zongyao Li | Daimeng Wei | Hengchao Shang | Xiaoyu Chen | Zhanglin Wu | Zhengzhe Yu | Jiaxin Guo | Minghan Wang | Lizhi Lei | Min Zhang | Hao Yang | Ying Qin
Proceedings of the Sixth Conference on Machine Translation

This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task. We participate in the Russian-to-Chinese task under the constrained condition. We use Transformer architecture and obtain the best performance via a variant with larger parameter sizes. We perform detailed data pre-processing and filtering on the provided large-scale bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, Data Denoising, Average Checkpoint, Ensemble, Fine-tuning, etc. Our system obtains 32.5 BLEU on the dev set and 27.7 BLEU on the test set, the highest score among all submissions.

pdf bib
HW-TSC’s Participation in the WMT 2021 Large-Scale Multilingual Translation Task
Zhengzhe Yu | Daimeng Wei | Zongyao Li | Hengchao Shang | Xiaoyu Chen | Zhanglin Wu | Jiaxin Guo | Minghan Wang | Lizhi Lei | Min Zhang | Hao Yang | Ying Qin
Proceedings of the Sixth Conference on Machine Translation

This paper presents the submission of Huawei Translation Services Center (HW-TSC) to the WMT 2021 Large-Scale Multilingual Translation Task. We participate in Samll Track #2, including 6 languages: Javanese (Jv), Indonesian (Id), Malay (Ms), Tagalog (Tl), Tamil (Ta) and English (En) with 30 directions under the constrained condition. We use Transformer architecture and obtain the best performance via multiple variants with larger parameter sizes. We train a single multilingual model to translate all the 30 directions. We perform detailed pre-processing and filtering on the provided large-scale bilingual and monolingual datasets. Several commonly used strategies are used to train our models, such as Back Translation, Forward Translation, Ensemble Knowledge Distillation, Adapter Fine-tuning. Our model obtains competitive results in the end.

pdf bib
HW-TSC’s Submissions to the WMT21 Biomedical Translation Task
Hao Yang | Zhanglin Wu | Zhengzhe Yu | Xiaoyu Chen | Daimeng Wei | Zongyao Li | Hengchao Shang | Minghan Wang | Jiaxin Guo | Lizhi Lei | Chuanfei Xu | Min Zhang | Ying Qin
Proceedings of the Sixth Conference on Machine Translation

This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC). Technical details are introduced in this paper, including model framework, data pre-processing method and model enhancement strategies. In addition, using the wmt20 OK-aligned biomedical test set, we compare and analyze system performances under different strategies. On WMT21 biomedical translation task, Our systems in English→Chinese and English→German directions get the highest BLEU scores among all submissions according to the official evaluation results.

pdf bib
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
Yimeng Chen | Chang Su | Yingtao Zhang | Yuxia Wang | Xiang Geng | Hao Yang | Shimin Tao | Guo Jiaxin | Wang Minghan | Min Zhang | Yujia Liu | Shujian Huang
Proceedings of the Sixth Conference on Machine Translation

This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task. We participated in all of the three sub-tasks, including Sentence-Level Direct Assessment (DA) task, Word and Sentence-Level Post-editing Effort task and Critical Error Detection task, in all language pairs. Our systems employ the framework of Predictor-Estimator, concretely with a pre-trained XLM-Roberta as Predictor and task-specific classifier or regressor as Estimator. For all tasks, we improve our systems by incorporating post-edit sentence or additional high-quality translation sentence in the way of multitask learning or encoding it with predictors directly. Moreover, in zero-shot setting, our data augmentation strategy based on Monte-Carlo Dropout brings up significant improvement on DA sub-task. Notably, our submissions achieve remarkable results over all tasks.

pdf bib
Code Summarization with Structure-induced Transformer
Hongqiu Wu | Hai Zhao | Min Zhang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction
Jinpeng Zhang | Baijun Ji | Nini Xiao | Xiangyu Duan | Min Zhang | Yangbin Shi | Weihua Luo
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing
Ying Li | Meishan Zhang | Zhenghua Li | Min Zhang | Zhefeng Wang | Baoxing Huai | Nicholas Jing Yuan
Findings of the Association for Computational Linguistics: EMNLP 2021

Thanks to the strong representation learning capability of deep learning, especially pre-training techniques with language model loss, dependency parsing has achieved great performance boost in the in-domain scenario with abundant labeled training data for target domains. However, the parsing community has to face the more realistic setting where the parsing performance drops drastically when labeled data only exists for several fixed out-domains. In this work, we propose a novel model for multi-source cross-domain dependency parsing. The model consists of two components, i.e., a parameter generation network for distinguishing domain-specific features, and an adversarial network for learning domain-invariant representations. Experiments on a recently released NLPCC-2019 dataset for multi-domain dependency parsing show that our model can consistently improve cross-domain parsing performance by about 2 points in averaged labeled attachment accuracy (LAS) over strong BERT-enhanced baselines. Detailed analysis is conducted to gain more insights on contributions of the two components.

pdf bib
Stacked AMR Parsing with Silver Data
Qingrong Xia | Zhenghua Li | Rui Wang | Min Zhang
Findings of the Association for Computational Linguistics: EMNLP 2021

Lacking sufficient human-annotated data is one main challenge for abstract meaning representation (AMR) parsing. To alleviate this problem, previous works usually make use of silver data or pre-trained language models. In particular, one recent seq-to-seq work directly fine-tunes AMR graph sequences on the encoder-decoder pre-trained language model and achieves new state-of-the-art results, outperforming previous works by a large margin. However, it makes the decoding relatively slower. In this work, we investigate alternative approaches to achieve competitive performance at faster speeds. We propose a simplified AMR parser and a pre-training technique for the effective usage of silver data. We conduct extensive experiments on the widely used AMR2.0 dataset and the results demonstrate that our Transformer-based AMR parser achieves the best performance among the seq2graph-based models. Furthermore, with silver data, our model achieves competitive results with the SOTA model, and the speed is an order of magnitude faster. Detailed analyses are conducted to gain more insights into our proposed model and the effectiveness of the pre-training technique.

pdf bib
Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation
Xinglin Lyu | Junhui Li | Zhengxian Gong | Min Zhang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recently a number of approaches have been proposed to improve translation performance for document-level neural machine translation (NMT). However, few are focusing on the subject of lexical translation consistency. In this paper we apply “one translation per discourse” in NMT, and aim to encourage lexical translation consistency for document-level NMT. This is done by first obtaining a word link for each source word in a document, which tells the positions where the source word appears. Then we encourage the translation of those words within a link to be consistent in two ways. On the one hand, when encoding sentences within a document we properly share context information of those words. On the other hand, we propose an auxiliary loss function to better constrain that their translation should be consistent. Experimental results on Chinese↔English and English→French translation tasks show that our approach not only achieves state-of-the-art performance in BLEU scores, but also greatly improves lexical consistency in translation.

pdf bib
Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection
Xincheng Ju | Dong Zhang | Rong Xiao | Junhui Li | Shoushan Li | Min Zhang | Guodong Zhou
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Aspect terms extraction (ATE) and aspect sentiment classification (ASC) are two fundamental and fine-grained sub-tasks in aspect-level sentiment analysis (ALSA). In the textual analysis, joint extracting both aspect terms and sentiment polarities has been drawn much attention due to the better applications than individual sub-task. However, in the multi-modal scenario, the existing studies are limited to handle each sub-task independently, which fails to model the innate connection between the above two objectives and ignores the better applications. Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA). Specifically, we first build an auxiliary text-image relation detection module to control the proper exploitation of visual information. Second, we adopt the hierarchical framework to bridge the multi-modal connection between MATE and MASC, as well as separately visual guiding for each sub module. Finally, we can obtain all aspect-level sentiment polarities dependent on the jointly extracted specific aspects. Extensive experiments show the effectiveness of our approach against the joint textual approaches, pipeline and collapsed multi-modal approaches.

pdf bib
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing
Kun Wu | Lijie Wang | Zhenghua Li | Ao Zhang | Xinyan Xiao | Hua Wu | Min Zhang | Haifeng Wang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Data augmentation has attracted a lot of research attention in the deep learning era for its ability in alleviating data sparseness. The lack of labeled data for unseen evaluation databases is exactly the major challenge for cross-domain text-to-SQL parsing. Previous works either require human intervention to guarantee the quality of generated data, or fail to handle complex SQL queries. This paper presents a simple yet effective data augmentation framework. First, given a database, we automatically produce a large number of SQL queries based on an abstract syntax tree grammar. For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries. Second, we propose a hierarchical SQL-to-question generation model to obtain high-quality natural language questions, which is the major contribution of this work. Finally, we design a simple sampling strategy that can greatly improve training efficiency given large amounts of generated data. Experiments on three cross-domain datasets, i.e., WikiSQL and Spider in English, and DuSQL in Chinese, show that our proposed data augmentation framework can consistently improve performance over strong baselines, and the hierarchical generation component is the key for the improvement.

2020

pdf bib
Improving Relation Extraction with Relational Paraphrase Sentences
Junjie Yu | Tong Zhu | Wenliang Chen | Wei Zhang | Min Zhang
Proceedings of the 28th International Conference on Computational Linguistics

Supervised models for Relation Extraction (RE) typically require human-annotated training data. Due to the limited size, the human-annotated data is usually incapable of covering diverse relation expressions, which could limit the performance of RE. To increase the coverage of relation expressions, we may enlarge the labeled data by hiring annotators or applying Distant Supervision (DS). However, the human-annotated data is costly and non-scalable while the distantly supervised data contains many noises. In this paper, we propose an alternative approach to improve RE systems via enriching diverse expressions by relational paraphrase sentences. Based on an existing labeled data, we first automatically build a task-specific paraphrase data. Then, we propose a novel model to learn the information of diverse relation expressions. In our model, we try to capture this information on the paraphrases via a joint learning framework. Finally, we conduct experiments on a widely used dataset and the experimental results show that our approach is effective to improve the performance on relation extraction, even compared with a strong baseline.

pdf bib
Multi-grained Chinese Word Segmentation with Weakly Labeled Data
Chen Gong | Zhenghua Li | Bowei Zou | Min Zhang
Proceedings of the 28th International Conference on Computational Linguistics

In contrast with the traditional single-grained word segmentation (SWS), where a sentence corresponds to a single word sequence, multi-grained Chinese word segmentation (MWS) aims to segment a sentence into multiple word sequences to preserve all words of different granularities. Due to the lack of manually annotated MWS data, previous work train and tune MWS models only on automatically generated pseudo MWS data. In this work, we further take advantage of the rich word boundary information in existing SWS data and naturally annotated data from dictionary example (DictEx) sentences, to advance the state-of-the-art MWS model based on the idea of weak supervision. Particularly, we propose to accommodate two types of weakly labeled data for MWS, i.e., SWS data and DictEx data by employing a simple yet competitive graph-based parser with local loss. Besides, we manually annotate a high-quality MWS dataset according to our newly compiled annotation guideline, consisting of over 9,000 sentences from two types of texts, i.e., canonical newswire (NEWS) and non-canonical web (BAIKE) data for better evaluation. Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1.12 and 5.97 on NEWS and BAIKE data in F1.

pdf bib
Semantic Role Labeling with Heterogeneous Syntactic Knowledge
Qingrong Xia | Rui Wang | Zhenghua Li | Yue Zhang | Min Zhang
Proceedings of the 28th International Conference on Computational Linguistics

Recently, due to the interplay between syntax and semantics, incorporating syntactic knowledge into neural semantic role labeling (SRL) has achieved much attention. Most of the previous syntax-aware SRL works focus on explicitly modeling homogeneous syntactic knowledge over tree outputs. In this work, we propose to encode heterogeneous syntactic knowledge for SRL from both explicit and implicit representations. First, we introduce graph convolutional networks to explicitly encode multiple heterogeneous dependency parse trees. Second, we extract the implicit syntactic representations from syntactic parser trained with heterogeneous treebanks. Finally, we inject the two types of heterogeneous syntax-aware representations into the base SRL model as extra inputs. We conduct experiments on two widely-used benchmark datasets, i.e., Chinese Proposition Bank 1.0 and English CoNLL-2005 dataset. Experimental results show that incorporating heterogeneous syntactic knowledge brings significant improvements over strong baselines. We further conduct detailed analysis to gain insights on the usefulness of heterogeneous (vs. homogeneous) syntactic knowledge and the effectiveness of our proposed approaches for modeling such knowledge.

pdf bib
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition
Huibin Ruan | Yu Hong | Yang Xu | Zhen Huang | Guodong Zhou | Min Zhang
Proceedings of the 28th International Conference on Computational Linguistics

We tackle implicit discourse relation recognition. Both self-attention and interactive-attention mechanisms have been applied for attention-aware representation learning, which improves the current discourse analysis models. To take advantages of the two attention mechanisms simultaneously, we develop a propagative attention learning model using a cross-coupled two-channel network. We experiment on Penn Discourse Treebank. The test results demonstrate that our model yields substantial improvements over the baselines (BiLSTM and BERT).

pdf bib
Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations
Ying Li | Zhenghua Li | Min Zhang
Proceedings of the 28th International Conference on Computational Linguistics

In recent years, parsing performance is dramatically improved on in-domain texts thanks to the rapid progress of deep neural network models. The major challenge for current parsing research is to improve parsing performance on out-of-domain texts that are very different from the in-domain training data when there is only a small-scale out-domain labeled data. To deal with this problem, we propose to improve the contextualized word representations via adversarial learning and fine-tuning BERT processes. Concretely, we apply adversarial learning to three representative semi-supervised domain adaption methods, i.e., direct concatenation (CON), feature augmentation (FA), and domain embedding (DE) with two useful strategies, i.e., fused target-domain word representations and orthogonality constraints, thus enabling to model more pure yet effective domain-specific and domain-invariant representations. Simultaneously, we utilize a large-scale target-domain unlabeled data to fine-tune BERT with only the language model loss, thus obtaining reliable contextualized word representations that benefit for the cross-domain dependency parsing. Experiments on a benchmark dataset show that our proposed adversarial approaches achieve consistent improvement, and fine-tuning BERT further boosts parsing accuracy by a large margin. Our single model achieves the same state-of-the-art performance as the top submitted system in the NLPCC-2019 shared task, which uses ensemble models and BERT.

pdf bib
Token Drop mechanism for Neural Machine Translation
Huaao Zhang | Shigui Qiu | Xiangyu Duan | Min Zhang
Proceedings of the 28th International Conference on Computational Linguistics

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token with a special token instead of setting zero to words. We further introduce two self-supervised objectives: Replaced Token Detection and Dropped Token Prediction. Our method aims to force model generating target translation with less information, in this way the model can learn textual representation better. Experiments on Chinese-English and English-Romanian benchmark demonstrate the effectiveness of our approach and our model achieves significant improvements over a strong Transformer baseline.

pdf bib
Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction
Tong Zhu | Haitao Wang | Junjie Yu | Xiabing Zhou | Wenliang Chen | Wei Zhang | Min Zhang
Proceedings of the 28th International Conference on Computational Linguistics

In recent years, distantly-supervised relation extraction has achieved a certain success by using deep neural networks. Distant Supervision (DS) can automatically generate large-scale annotated data by aligning entity pairs from Knowledge Bases (KB) to sentences. However, these DS-generated datasets inevitably have wrong labels that result in incorrect evaluation scores during testing, which may mislead the researchers. To solve this problem, we build a new dataset NYTH, where we use the DS-generated data as training data and hire annotators to label test data. Compared with the previous datasets, NYT-H has a much larger test set and then we can perform more accurate and consistent evaluation. Finally, we present the experimental results of several widely used systems on NYT-H. The experimental results show that the ranking lists of the comparison systems on the DS-labelled test data and human-annotated test data are different. This indicates that our human-annotated data is necessary for evaluation of distantly-supervised relation extraction.

pdf bib
Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences
Xiangyu Duan | Baijun Ji | Hao Jia | Min Tan | Min Zhang | Boxing Chen | Weihua Luo | Yue Zhang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary. Motivated by the ability of a monolingual speaker learning to translate via looking up the bilingual dictionary, we propose the task to see how much potential an MT system can attain using the bilingual dictionary and large scale monolingual corpora, while is independent on parallel sentences. We propose anchored training (AT) to tackle the task. AT uses the bilingual dictionary to establish anchoring points for closing the gap between source language and target language. Experiments on various language pairs show that our approaches are significantly better than various baselines, including dictionary-based word-by-word translation, dictionary-supervised cross-lingual word embedding transformation, and unsupervised MT. On distant language pairs that are hard for unsupervised MT to perform well, AT performs remarkably better, achieving performances comparable to supervised SMT trained on more than 4M parallel sentences.

pdf bib
Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks
Bo Zhang | Yue Zhang | Rui Wang | Zhenghua Li | Min Zhang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Opinion role labeling (ORL) is a fine-grained opinion analysis task and aims to answer “who expressed what kind of sentiment towards what?”. Due to the scarcity of labeled data, ORL remains challenging for data-driven methods. In this work, we try to enhance neural ORL models with syntactic knowledge by comparing and integrating different representations. We also propose dependency graph convolutional networks (DEPGCN) to encode parser information at different processing levels. In order to compensate for parser inaccuracy and reduce error propagation, we introduce multi-task learning (MTL) to train the parser and the ORL model simultaneously. We verify our methods on the benchmark MPQA corpus. The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9.29 over the syntax-agnostic baseline. In addition, we find that the contributions from syntactic knowledge do not fully overlap with contextualized word representations (BERT). Our best model achieves 4.34 higher F1 score than the current state-ofthe-art.

pdf bib
Efficient Second-Order TreeCRF for Neural Dependency Parsing
Yu Zhang | Zhenghua Li | Min Zhang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

In the deep learning (DL) era, parsing models are extremely simplified with little hurt on performance, thanks to the remarkable capability of multi-layer BiLSTMs in context representation. As the most popular graph-based dependency parser due to its high efficiency and performance, the biaffine parser directly scores single dependencies under the arc-factorization assumption, and adopts a very simple local token-wise cross-entropy training loss. This paper for the first time presents a second-order TreeCRF extension to the biaffine parser. For a long time, the complexity and inefficiency of the inside-outside algorithm hinder the popularity of TreeCRF. To address this issue, we propose an effective way to batchify the inside and Viterbi algorithms for direct large matrix operation on GPUs, and to avoid the complex outside algorithm via efficient back-propagation. Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data. We release our code at https://github.com/yzhangcs/crfpar.

pdf bib
Aspect Sentiment Classification with Document-level Sentiment Preference Modeling
Xiao Chen | Changlong Sun | Jingjing Wang | Shoushan Li | Luo Si | Min Zhang | Guodong Zhou
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

In the literature, existing studies always consider Aspect Sentiment Classification (ASC) as an independent sentence-level classification problem aspect by aspect, which largely ignore the document-level sentiment preference information, though obviously such information is crucial for alleviating the information deficiency problem in ASC. In this paper, we explore two kinds of sentiment preference information inside a document, i.e., contextual sentiment consistency w.r.t. the same aspect (namely intra-aspect sentiment consistency) and contextual sentiment tendency w.r.t. all the related aspects (namely inter-aspect sentiment tendency). On the basis, we propose a Cooperative Graph Attention Networks (CoGAN) approach for cooperatively learning the aspect-related sentence representation. Specifically, two graph attention networks are leveraged to model above two kinds of document-level sentiment preference information respectively, followed by an interactive mechanism to integrate the two-fold preference. Detailed evaluation demonstrates the great advantage of the proposed approach to ASC over the state-of-the-art baselines. This justifies the importance of the document-level sentiment preference information to ASC and the effectiveness of our approach capturing such information.

pdf bib
Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue
WeiSheng Zhang | Kaisong Song | Yangyang Kang | Zhongqing Wang | Changlong Sun | Xiaozhong Liu | Shoushan Li | Min Zhang | Luo Si
Findings of the Association for Computational Linguistics: EMNLP 2020

As an important research topic, customer service dialogue generation tends to generate generic seller responses by leveraging current dialogue information. In this study, we propose a novel and extensible dialogue generation method by leveraging sellers’ historical dialogue information, which can be both accessible and informative. By utilizing innovative historical dialogue representation learning and historical dialogue selection mechanism, the proposed model is capable of detecting most related responses from sellers’ historical dialogues, which can further enhance the current dialogue generation quality. Unlike prior dialogue generation efforts, we treat each seller’s historical dialogues as a list of Customer-Seller utterance pairs and allow the model to measure their different importance, and copy words directly from most relevant pairs. Extensive experimental results show that the proposed approach can generate high-quality responses that cater to specific sellers’ characteristics and exhibit consistent superiority over baselines on a real-world multi-turn customer service dialogue dataset.

pdf bib
Improving AMR Parsing with Sequence-to-Sequence Pre-training
Dongqin Xu | Junhui Li | Muhua Zhu | Min Zhang | Guodong Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance. To alleviate such data size restriction, pre-trained models have been drawing more and more attention in AMR parsing. However, previous pre-trained models, like BERT, are implemented for general purpose which may not work as expected for the specific task of AMR parsing. In this paper, we focus on sequence-to-sequence (seq2seq) AMR parsing and propose a seq2seq pre-training approach to build pre-trained models in both single and joint way on three relevant tasks, i.e., machine translation, syntactic parsing, and AMR parsing itself. Moreover, we extend the vanilla fine-tuning method to a multi-task learning fine-tuning method that optimizes for the performance of AMR parsing while endeavors to preserve the response of pre-trained models. Extensive experimental results on two English benchmark datasets show that both the single and joint pre-trained models significantly improve the performance (e.g., from 71.5 to 80.2 on AMR 2.0), which reaches the state of the art. The result is very encouraging since we achieve this with seq2seq models rather than complex models. We make our code and model available at https://github.com/xdqkid/S2S-AMR-Parser.

pdf bib
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
Lijie Wang | Ao Zhang | Kun Wu | Ke Sun | Zhenghua Li | Hua Wu | Min Zhang | Haifeng Wang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Due to the lack of labeled data, previous research on text-to-SQL parsing mainly focuses on English. Representative English datasets include ATIS, WikiSQL, Spider, etc. This paper presents DuSQL, a larges-scale and pragmatic Chinese dataset for the cross-domain text-to-SQL task, containing 200 databases, 813 tables, and 23,797 question/SQL pairs. Our new dataset has three major characteristics. First, by manually analyzing questions from several representative applications, we try to figure out the true distribution of SQL queries in real-life needs. Second, DuSQL contains a considerable proportion of SQL queries involving row or column calculations, motivated by our analysis on the SQL query distributions. Finally, we adopt an effective data construction framework via human-computer collaboration. The basic idea is automatically generating SQL queries based on the SQL grammar and constrained by the given database. This paper describes in detail the construction process and data statistics of DuSQL. Moreover, we present and compare performance of several open-source text-to-SQL parsers with minor modification to accommodate Chinese, including a simple yet effective extension to IRNet for handling calculation SQL queries.

2019

pdf bib
HLT@SUDA at SemEval-2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing
Wei Jiang | Zhenghua Li | Yu Zhang | Min Zhang
Proceedings of the 13th International Workshop on Semantic Evaluation

This paper describes a simple UCCA semantic graph parsing approach. The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery. In this way, we can make use of existing syntactic parsing techniques. Based on the data statistics, we recover discontinuous nodes directly according to the output labels of the constituent parser and use a biaffine classification model to recover the more complex remote edges. The classification model and the constituent parser are simultaneously trained under the multi-task learning framework. We use the multilingual BERT as extra features in the open tracks. Our system ranks the first place in the six English/German closed/open tracks among seven participating systems. For the seventh cross-lingual track, where there is little training data for French, we propose a language embedding approach to utilize English and German training data, and our result ranks the second place.

pdf bib
Semi-supervised Domain Adaptation for Dependency Parsing
Zhenghua Li | Xue Peng | Min Zhang | Rui Wang | Luo Si
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

During the past decades, due to the lack of sufficient labeled data, most studies on cross-domain parsing focus on unsupervised domain adaptation, assuming there is no target-domain training data. However, unsupervised approaches make limited progress so far due to the intrinsic difficulty of both domain adaptation and parsing. This paper tackles the semi-supervised domain adaptation problem for Chinese dependency parsing, based on two newly-annotated large-scale domain-aware datasets. We propose a simple domain embedding approach to merge the source- and target-domain training data, which is shown to be more effective than both direct corpus concatenation and multi-task learning. In order to utilize unlabeled target-domain data, we employ the recent contextualized word representations and show that a simple fine-tuning procedure can further boost cross-domain parsing accuracy by large margin.

pdf bib
Sentence-Level Agreement for Neural Machine Translation
Mingming Yang | Rui Wang | Kehai Chen | Masao Utiyama | Eiichiro Sumita | Min Zhang | Tiejun Zhao
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references. In NMT, there is a natural correspondence between the source sentence and the target sentence. However, this relationship has only been represented using the entire neural network and the training objective is computed in word-level. In this paper, we propose a sentence-level agreement module to directly minimize the difference between the representation of source and target sentence. The proposed agreement module can be integrated into NMT as an additional training objective function and can also be used to enhance the representation of the source sentences. Empirical results on the NIST Chinese-to-English and WMT English-to-German tasks show the proposed agreement module can significantly improve the NMT performance.

pdf bib
Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention
Xiangyu Duan | Mingming Yin | Min Zhang | Boxing Chen | Weihua Luo
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Abstractive Sentence Summarization (ASSUM) targets at grasping the core idea of the source sentence and presenting it as the summary. It is extensively studied using statistical models or neural models based on the large-scale monolingual source-summary parallel corpus. But there is no cross-lingual parallel corpus, whose source sentence language is different to the summary language, to directly train a cross-lingual ASSUM system. We propose to solve this zero-shot problem by using resource-rich monolingual ASSUM system to teach zero-shot cross-lingual ASSUM system on both summary word generation and attention. This teaching process is along with a back-translation process which simulates source-summary pairs. Experiments on cross-lingual ASSUM task show that our proposed method is significantly better than pipeline baselines and previous works, and greatly enhances the cross-lingual performances closer to the monolingual performances.

pdf bib
Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network
Jingjing Wang | Changlong Sun | Shoushan Li | Xiaozhong Liu | Luo Si | Min Zhang | Guodong Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

In the literature, existing studies on aspect sentiment classification (ASC) focus on individual non-interactive reviews. This paper extends the research to interactive reviews and proposes a new research task, namely Aspect Sentiment Classification towards Question-Answering (ASC-QA), for real-world applications. This new task aims to predict sentiment polarities for specific aspects from interactive QA style reviews. In particular, a high-quality annotated corpus is constructed for ASC-QA to facilitate corresponding research. On this basis, a Reinforced Bidirectional Attention Network (RBAN) approach is proposed to address two inherent challenges in ASC-QA, i.e., semantic matching between question and answer, and data noise. Experimental results demonstrate the great advantage of the proposed approach to ASC-QA against several state-of-the-art baselines.

pdf bib
SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT
Yue Zhang | Wei Jiang | Qingrong Xia | Junjie Cao | Rui Wang | Zhenghua Li | Min Zhang
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning

In this paper, we describe our participating systems in the shared task on Cross- Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). The task includes five frameworks for graph-based meaning representations, i.e., DM, PSD, EDS, UCCA, and AMR. One common characteristic of our systems is that we employ graph-based methods instead of transition-based methods when predicting edges between nodes. For SDP, we jointly perform edge prediction, frame tagging, and POS tagging via multi-task learning (MTL). For UCCA, we also jointly model a constituent tree parsing and a remote edge recovery task. For both EDS and AMR, we produce nodes first and edges second in a pipeline fashion. External resources like BERT are found helpful for all frameworks except AMR. Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.

pdf bib
Code-Switching for Enhancing NMT with Pre-Specified Translation
Kai Song | Yue Zhang | Heng Yu | Weihua Luo | Kun Wang | Min Zhang
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during decoding. Both methods can hurt translation fidelity for various reasons. We investigate a data augmentation method, making code-switched training data by replacing source phrases with their target translations. Our method does not change the MNT model or decoding algorithm, allowing the model to learn lexicon translations by copying source-side target words. Extensive experiments show that our method achieves consistent improvements over existing approaches, improving translation of constrained words without hurting unconstrained words.

pdf bib
Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations
Meishan Zhang | Zhenghua Li | Guohong Fu | Min Zhang
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Syntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN and Tree-Linearization methods, which may suffer from error propagation. In this work, we propose a novel method to integrate source-side syntax implicitly for NMT. The basic idea is to use the intermediate hidden representations of a well-trained end-to-end dependency parser, which are referred to as syntax-aware word representations (SAWRs). Then, we simply concatenate such SAWRs with ordinary word embeddings to enhance basic NMT models. The method can be straightforwardly integrated into the widely-used sequence-to-sequence (Seq2Seq) NMT models. We start with a representative RNN-based Seq2Seq baseline system, and test the effectiveness of our proposed method on two benchmark datasets of the Chinese-English and English-Vietnamese translation tasks, respectively. Experimental results show that the proposed approach is able to bring significant BLEU score improvements on the two datasets compared with the baseline, 1.74 points for Chinese-English translation and 0.80 point for English-Vietnamese translation, respectively. In addition, the approach also outperforms the explicit Tree-RNN and Tree-Linearization methods.

pdf bib
Contrastive Attention Mechanism for Abstractive Sentence Summarization
Xiangyu Duan | Hongfei Yu | Mingming Yin | Min Zhang | Weihua Luo | Yue Zhang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We propose a contrastive attention mechanism to extend the sequence-to-sequence framework for abstractive sentence summarization task, which aims to generate a brief summary of a given source sentence. The proposed contrastive attention mechanism accommodates two categories of attention: one is the conventional attention that attends to relevant parts of the source sentence, the other is the opponent attention that attends to irrelevant or less relevant parts of the source sentence. Both attentions are trained in an opposite way so that the contribution from the conventional attention is encouraged and the contribution from the opponent attention is discouraged through a novel softmax and softmin functionality. Experiments on benchmark datasets show that, the proposed contrastive attention mechanism is more focused on the relevant parts for the summary than the conventional attention mechanism, and greatly advances the state-of-the-art performance on the abstractive sentence summarization task. We release the code at https://github.com/travel-go/ Abstractive-Text-Summarization.

pdf bib
A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling
Qingrong Xia | Zhenghua Li | Min Zhang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Semantic role labeling (SRL) aims to identify the predicate-argument structure of a sentence. Inspired by the strong correlation between syntax and semantics, previous works pay much attention to improve SRL performance on exploiting syntactic knowledge, achieving significant results. Pipeline methods based on automatic syntactic trees and multi-task learning (MTL) approaches using standard syntactic trees are two common research orientations. In this paper, we adopt a simple unified span-based model for both span-based and word-based Chinese SRL as a strong baseline. Besides, we present a MTL framework that includes the basic SRL module and a dependency parser module. Different from the commonly used hard parameter sharing strategy in MTL, the main idea is to extract implicit syntactic representations from the dependency parser as external inputs for the basic SRL model. Experiments on the benchmarks of Chinese Proposition Bank 1.0 and CoNLL-2009 Chinese datasets show that our proposed framework can effectively improve the performance over the strong baselines. With the external BERT representations, our framework achieves new state-of-the-art 87.54 and 88.5 F1 scores on the two test data of the two benchmarks, respectively. In-depth analysis are conducted to gain more insights on the proposed framework and the effectiveness of syntax.

pdf bib
Modeling Graph Structure in Transformer for Better AMR-to-Text Generation
Jie Zhu | Junhui Li | Muhua Zhu | Longhua Qian | Min Zhang | Guodong Zhou
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Recent studies on AMR-to-text generation often formalize the task as a sequence-to-sequence (seq2seq) learning problem by converting an Abstract Meaning Representation (AMR) graph into a word sequences. Graph structures are further modeled into the seq2seq framework in order to utilize the structural information in the AMR graphs. However, previous approaches only consider the relations between directly connected concepts while ignoring the rich structure in AMR graphs. In this paper we eliminate such a strong limitation and propose a novel structure-aware self-attention approach to better model the relations between indirectly connected concepts in the state-of-the-art seq2seq model, i.e. the Transformer. In particular, a few different methods are explored to learn structural representations between two concepts. Experimental results on English AMR benchmark datasets show that our approach significantly outperforms the state-of-the-art with 29.66 and 31.82 BLEU scores on LDC2015E86 and LDC2017T10, respectively. To the best of our knowledge, these are the best results achieved so far by supervised models on the benchmarks.

pdf bib
Emotion Detection with Neural Personal Discrimination
Xiabing Zhou | Zhongqing Wang | Shoushan Li | Guodong Zhou | Min Zhang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

There have been a recent line of works to automatically predict the emotions of posts in social media. Existing approaches consider the posts individually and predict their emotions independently. Different from previous researches, we explore the dependence among relevant posts via the authors’ backgrounds, since the authors with similar backgrounds, e.g., gender, location, tend to express similar emotions. However, such personal attributes are not easy to obtain in most social media websites, and it is hard to capture attributes-aware words to connect similar people. Accordingly, we propose a Neural Personal Discrimination (NPD) approach to address above challenges by determining personal attributes from posts, and connecting relevant posts with similar attributes to jointly learn their emotions. In particular, we employ adversarial discriminators to determine the personal attributes, with attention mechanisms to aggregate attributes-aware words. In this way, social correlationship among different posts can be better addressed. Experimental results show the usefulness of personal attributes, and the effectiveness of our proposed NPD approach in capturing such personal attributes with significant gains over the state-of-the-art models.

pdf bib
Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning
Jingjing Wang | Changlong Sun | Shoushan Li | Jiancheng Wang | Luo Si | Min Zhang | Xiaozhong Liu | Guodong Zhou
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Recently, neural networks have shown promising results on Document-level Aspect Sentiment Classification (DASC). However, these approaches often offer little transparency w.r.t. their inner working mechanisms and lack interpretability. In this paper, to simulating the steps of analyzing aspect sentiment in a document by human beings, we propose a new Hierarchical Reinforcement Learning (HRL) approach to DASC. This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC. First, a high-level policy is proposed to select aspect-relevant clauses and discard noisy clauses. Then, a low-level policy is proposed to select sentiment-relevant words and discard noisy words inside the selected clauses. Finally, a sentiment rating predictor is designed to provide reward signals to guide both clause and word selection. Experimental results demonstrate the impressive effectiveness of the proposed approach to DASC over the state-of-the-art baselines.

2018

pdf bib
Supervised Treebank Conversion: Data and Approaches
Xinzhou Jiang | Zhenghua Li | Bo Zhang | Min Zhang | Sheng Li | Luo Si
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Treebank conversion is a straightforward and effective way to exploit various heterogeneous treebanks for boosting parsing performance. However, previous work mainly focuses on unsupervised treebank conversion and has made little progress due to the lack of manually labeled data where each sentence has two syntactic trees complying with two different guidelines at the same time, referred as bi-tree aligned data. In this work, we for the first time propose the task of supervised treebank conversion. First, we manually construct a bi-tree aligned dataset containing over ten thousand sentences. Then, we propose two simple yet effective conversion approaches (pattern embedding and treeLSTM) based on the state-of-the-art deep biaffine parser. Experimental results show that 1) the two conversion approaches achieve comparable conversion accuracy, and 2) treebank conversion is superior to the widely used multi-task learning framework in multi-treebank exploitation and leads to significantly higher parsing accuracy.

pdf bib
Distantly Supervised NER with Partial Annotation Learning and Reinforcement Learning
Yaosheng Yang | Wenliang Chen | Zhenghua Li | Zhengqiu He | Min Zhang
Proceedings of the 27th International Conference on Computational Linguistics

A bottleneck problem with Chinese named entity recognition (NER) in new domains is the lack of annotated data. One solution is to utilize the method of distant supervision, which has been widely used in relation extraction, to automatically populate annotated training data without humancost. The distant supervision assumption here is that if a string in text is included in a predefined dictionary of entities, the string might be an entity. However, this kind of auto-generated data suffers from two main problems: incomplete and noisy annotations, which affect the performance of NER models. In this paper, we propose a novel approach which can partially solve the above problems of distant supervision for NER. In our approach, to handle the incomplete problem, we apply partial annotation learning to reduce the effect of unknown labels of characters. As for noisy annotation, we design an instance selector based on reinforcement learning to distinguish positive sentences from auto-generated annotations. In experiments, we create two datasets for Chinese named entity recognition in two domains with the help of distant supervision. The experimental results show that the proposed approach obtains better performance than the comparison systems on both two datasets.

pdf bib
One vs. Many QA Matching with both Word-level and Sentence-level Attention Network
Lu Wang | Shoushan Li | Changlong Sun | Luo Si | Xiaozhong Liu | Min Zhang | Guodong Zhou
Proceedings of the 27th International Conference on Computational Linguistics

Question-Answer (QA) matching is a fundamental task in the Natural Language Processing community. In this paper, we first build a novel QA matching corpus with informal text which is collected from a product reviewing website. Then, we propose a novel QA matching approach, namely One vs. Many Matching, which aims to address the novel scenario where one question sentence often has an answer with multiple sentences. Furthermore, we improve our matching approach by employing both word-level and sentence-level attentions for solving the noisy problem in the informal text. Empirical studies demonstrate the effectiveness of the proposed approach to question-answer matching.

pdf bib
Adaptive Weighting for Neural Machine Translation
Yachao Li | Junhui Li | Min Zhang
Proceedings of the 27th International Conference on Computational Linguistics

In the popular sequence to sequence (seq2seq) neural machine translation (NMT), there exist many weighted sum models (WSMs), each of which takes a set of input and generates one output. However, the weights in a WSM are independent of each other and fixed for all inputs, suggesting that by ignoring different needs of inputs, the WSM lacks effective control on the influence of each input. In this paper, we propose adaptive weighting for WSMs to control the contribution of each input. Specifically, we apply adaptive weighting for both GRU and the output state in NMT. Experimentation on Chinese-to-English translation and English-to-German translation demonstrates that the proposed adaptive weighting is able to much improve translation accuracy by achieving significant improvement of 1.49 and 0.92 BLEU points for the two translation tasks. Moreover, we discuss in-depth on what type of information is encoded in the encoder and how information influences the generation of target words in the decoder.

pdf bib
M-CNER: A Corpus for Chinese Named Entity Recognition in Multi-Domains
Qi Lu | YaoSheng Yang | Zhenghua Li | Wenliang Chen | Min Zhang
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Proceedings of the Seventh Named Entities Workshop
Nancy Chen | Rafael E. Banchs | Xiangyu Duan | Min Zhang | Haizhou Li
Proceedings of the Seventh Named Entities Workshop

pdf bib
NEWS 2018 Whitepaper
Nancy Chen | Xiangyu Duan | Min Zhang | Rafael E. Banchs | Haizhou Li
Proceedings of the Seventh Named Entities Workshop

Transliteration is defined as phonetic translation of names across languages. Transliteration of Named Entities (NEs) is necessary in many applications, such as machine translation, corpus alignment, cross-language IR, information extraction and automatic lexicon acquisition. All such systems call for high-performance transliteration, which is the focus of shared task in the NEWS 2018 workshop. The objective of the shared task is to promote machine transliteration research by providing a common benchmarking platform for the community to evaluate the state-of-the-art technologies.

pdf bib
Report of NEWS 2018 Named Entity Transliteration Shared Task
Nancy Chen | Rafael E. Banchs | Min Zhang | Xiangyu Duan | Haizhou Li
Proceedings of the Seventh Named Entities Workshop

This report presents the results from the Named Entity Transliteration Shared Task conducted as part of The Seventh Named Entities Workshop (NEWS 2018) held at ACL 2018 in Melbourne, Australia. Similar to previous editions of NEWS, the Shared Task featured 19 tasks on proper name transliteration, including 13 different languages and two different Japanese scripts. A total of 6 teams from 8 different institutions participated in the evaluation, submitting 424 runs, involving different transliteration methodologies. Four performance metrics were used to report the evaluation results. The NEWS shared task on machine transliteration has successfully achieved its objectives by providing a common ground for the research community to conduct comparative evaluations of state-of-the-art technologies that will benefit the future research and development in this area.

pdf bib
Improving the Transformer Translation Model with Document-Level Context
Jiacheng Zhang | Huanbo Luan | Maosong Sun | Feifei Zhai | Jingfang Xu | Min Zhang | Yang Liu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge. In this work, we extend the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder. As large-scale document-level parallel corpora are usually not available, we introduce a two-step training method to take full advantage of abundant sentence-level parallel corpora and limited document-level parallel corpora. Experiments on the NIST Chinese-English datasets and the IWSLT French-English datasets show that our approach improves over Transformer significantly.

pdf bib
Using active learning to expand training data for implicit discourse relation recognition
Yang Xu | Yu Hong | Huibin Ruan | Jianmin Yao | Min Zhang | Guodong Zhou
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We tackle discourse-level relation recognition, a problem of determining semantic relations between text spans. Implicit relation recognition is challenging due to the lack of explicit relational clues. The increasingly popular neural network techniques have been proven effective for semantic encoding, whereby widely employed to boost semantic relation discrimination. However, learning to predict semantic relations at a deep level heavily relies on a great deal of training data, but the scale of the publicly available data in this field is limited. In this paper, we follow Rutherford and Xue (2015) to expand the training data set using the corpus of explicitly-related arguments, by arbitrarily dropping the overtly presented discourse connectives. On the basis, we carry out an experiment of sampling, in which a simple active learning approach is used, so as to take the informative instances for data expansion. The goal is to verify whether the selective use of external data not only reduces the time consumption of retraining but also ensures a better system performance. Using the expanded training data, we retrain a convolutional neural network (CNN) based classifer which is a simplified version of Qin et al. (2016)’s stacking gated relation recognizer. Experimental results show that expanding the training set with small-scale carefully-selected external data yields substantial performance gain, with the improvements of about 4% for accuracy and 3.6% for F-score. This allows a weak classifier to achieve a comparable performance against the state-of-the-art systems.

pdf bib
Sentiment Classification towards Question-Answering with Hierarchical Matching Network
Chenlin Shen | Changlong Sun | Jingjing Wang | Yangyang Kang | Shoushan Li | Xiaozhong Liu | Luo Si | Min Zhang | Guodong Zhou
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In an e-commerce environment, user-oriented question-answering (QA) text pair could carry rich sentiment information. In this study, we propose a novel task/method to address QA sentiment analysis. In particular, we create a high-quality annotated corpus with specially-designed annotation guidelines for QA-style sentiment classification. On the basis, we propose a three-stage hierarchical matching network to explore deep sentiment information in a QA text pair. First, we segment both the question and answer text into sentences and construct a number of [Q-sentence, A-sentence] units in each QA text pair. Then, by leveraging a QA bidirectional matching layer, the proposed approach can learn the matching vectors of each [Q-sentence, A-sentence] unit. Finally, we characterize the importance of the generated matching vectors via a self-matching attention layer. Experimental results, comparing with a number of state-of-the-art baselines, demonstrate the impressive effectiveness of the proposed approach for QA-style sentiment classification.

2017

pdf bib
Dependency Parsing with Partial Annotations: An Empirical Comparison
Yue Zhang | Zhenghua Li | Jun Lang | Qingrong Xia | Min Zhang
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

This paper describes and compares two straightforward approaches for dependency parsing with partial annotations (PA). The first approach is based on a forest-based training objective for two CRF parsers, i.e., a biaffine neural network graph-based parser (Biaffine) and a traditional log-linear graph-based parser (LLGPar). The second approach is based on the idea of constrained decoding for three parsers, i.e., a traditional linear graph-based parser (LGPar), a globally normalized neural network transition-based parser (GN3Par) and a traditional linear transition-based parser (LTPar). For the test phase, constrained decoding is also used for completing partial trees. We conduct experiments on Penn Treebank under three different settings for simulating PA, i.e., random, most uncertain, and divergent outputs from the five parsers. The results show that LLGPar is most effective in directly learning from PA, and other parsers can achieve best performance when PAs are completed into full trees by LLGPar.

pdf bib
Multi-Grained Chinese Word Segmentation
Chen Gong | Zhenghua Li | Min Zhang | Xinzhou Jiang
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Traditionally, word segmentation (WS) adopts the single-grained formalism, where a sentence corresponds to a single word sequence. However, Sproat et al. (1997) show that the inter-native-speaker consistency ratio over Chinese word boundaries is only 76%, indicating single-grained WS (SWS) imposes unnecessary challenges on both manual annotation and statistical modeling. Moreover, WS results of different granularities can be complementary and beneficial for high-level applications. This work proposes and addresses multi-grained WS (MWS). We build a large-scale pseudo MWS dataset for model training and tuning by leveraging the annotation heterogeneity of three SWS datasets. Then we manually annotate 1,500 test sentences with true MWS annotations. Finally, we propose three benchmark approaches by casting MWS as constituent parsing and sequence labeling. Experiments and analysis lead to many interesting findings.

pdf bib
Translating Phrases in Neural Machine Translation
Xing Wang | Zhaopeng Tu | Deyi Xiong | Min Zhang
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Phrases play an important role in natural language understanding and machine translation (Sag et al., 2002; Villavicencio et al., 2005). However, it is difficult to integrate them into current neural machine translation (NMT) which reads and generates sentences word by word. In this work, we propose a method to translate phrases in NMT by integrating a phrase memory storing target phrases from a phrase-based statistical machine translation (SMT) system into the encoder-decoder architecture of NMT. At each decoding step, the phrase memory is first re-written by the SMT model, which dynamically generates relevant target phrases with contextual information provided by the NMT model. Then the proposed model reads the phrase memory to make probability estimations for all phrases in the phrase memory. If phrase generation is carried on, the NMT decoder selects an appropriate phrase from the memory to perform phrase translation and updates its decoding state by consuming the words in the selected phrase. Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does. Experiment results on the Chinese to English translation show that the proposed model achieves significant improvements over the baseline on various test sets.

pdf bib
Modeling Source Syntax for Neural Machine Translation
Junhui Li | Deyi Xiong | Zhaopeng Tu | Muhua Zhu | Min Zhang | Guodong Zhou
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly incorporated into NMT effectively to provide further improvements. Specifically, we linearize parse trees of source sentences to obtain structural label sequences. On the basis, we propose three different sorts of encoders to incorporate source syntax into NMT: 1) Parallel RNN encoder that learns word and label annotation vectors parallelly; 2) Hierarchical RNN encoder that learns word and label annotation vectors in a two-level hierarchy; and 3) Mixed RNN encoder that stitchingly learns word and label annotation vectors over sequences where words and labels are mixed. Experimentation on Chinese-to-English translation demonstrates that all the three proposed syntactic encoders are able to improve translation accuracy. It is interesting to note that the simplest RNN encoder, i.e., Mixed RNN encoder yields the best performance with an significant improvement of 1.4 BLEU points. Moreover, an in-depth analysis from several perspectives is provided to reveal how source syntax benefits NMT.

2016

pdf bib
Variational Neural Discourse Relation Recognizer
Biao Zhang | Deyi Xiong | Jinsong Su | Qun Liu | Rongrong Ji | Hong Duan | Min Zhang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Variational Neural Machine Translation
Biao Zhang | Deyi Xiong | Jinsong Su | Hong Duan | Min Zhang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Fast Coupled Sequence Labeling on Heterogeneous Annotations via Context-aware Pruning
Zhenghua Li | Jiayuan Chao | Min Zhang | Jiwen Yang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Proceedings of the Sixth Named Entity Workshop
Xiangyu Duan | Rafael E. Banchs | Min Zhang | Haizhou Li | A Kumaran
Proceedings of the Sixth Named Entity Workshop

pdf bib
Whitepaper of NEWS 2016 Shared Task on Machine Transliteration
Xiangyu Duan | Min Zhang | Haizhou Li | Rafael Banchs | A Kumaran
Proceedings of the Sixth Named Entity Workshop

pdf bib
Report of NEWS 2016 Machine Transliteration Shared Task
Xiangyu Duan | Rafael Banchs | Min Zhang | Haizhou Li | A. Kumaran
Proceedings of the Sixth Named Entity Workshop

pdf bib
Learning Event Expressions via Bilingual Structure Projection
Fangyuan Li | Ruihong Huang | Deyi Xiong | Min Zhang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Identifying events of a specific type is a challenging task as events in texts are described in numerous and diverse ways. Aiming to resolve high complexities of event descriptions, previous work (Huang and Riloff, 2013) proposes multi-faceted event recognition and a bootstrapping method to automatically acquire both event facet phrases and event expressions from unannotated texts. However, to ensure high quality of learned phrases, this method is constrained to only learn phrases that match certain syntactic structures. In this paper, we propose a bilingual structure projection algorithm that explores linguistic divergences between two languages (Chinese and English) and mines new phrases with new syntactic structures, which have been ignored in the previous work. Experiments show that our approach can successfully find novel event phrases and structures, e.g., phrases headed by nouns. Furthermore, the newly mined phrases are capable of recognizing additional event descriptions and increasing the recall of event recognition.

pdf bib
Distributed Representations for Building Profiles of Users and Items from Text Reviews
Wenliang Chen | Zhenjie Zhang | Zhenghua Li | Min Zhang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

In this paper, we propose an approach to learn distributed representations of users and items from text comments for recommendation systems. Traditional recommendation algorithms, e.g. collaborative filtering and matrix completion, are not designed to exploit the key information hidden in the text comments, while existing opinion mining methods do not provide direct support to recommendation systems with useful features on users and items. Our approach attempts to construct vectors to represent profiles of users and items under a unified framework to maximize word appearance likelihood. Then, the vector representations are used for a recommendation task in which we predict scores on unobserved user-item pairs without given texts. The recommendation-aware distributed representation approach is fully supported by effective and efficient learning algorithms over massive text archive. Our empirical evaluations on real datasets show that our system outperforms the state-of-the-art baseline systems.

pdf bib
Improving Statistical Machine Translation with Selectional Preferences
Haiqing Tang | Deyi Xiong | Min Zhang | Zhengxian Gong
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Long-distance semantic dependencies are crucial for lexical choice in statistical machine translation. In this paper, we study semantic dependencies between verbs and their arguments by modeling selectional preferences in the context of machine translation. We incorporate preferences that verbs impose on subjects and objects into translation. In addition, bilingual selectional preferences between source-side verbs and target-side arguments are also investigated. Our experiments on Chinese-to-English translation tasks with large-scale training data demonstrate that statistical machine translation using verbal selectional preferences can achieve statistically significant improvements over a state-of-the-art baseline.

pdf bib
Bilingual Autoencoders with Global Descriptors for Modeling Parallel Sentences
Biao Zhang | Deyi Xiong | Jinsong Su | Hong Duan | Min Zhang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing. In this paper, we explore a bilingual autoencoder approach to model parallel sentences. We extract sentence-level global descriptors (e.g. min, max) from word embeddings, and construct two monolingual autoencoders over these descriptors on the source and target language. In order to tightly connect the two autoencoders with bilingual correspondences, we force them to share the same decoding parameters and minimize a corpus-level semantic distance between the two languages. Being optimized towards a joint objective function of reconstruction and semantic errors, our bilingual antoencoder is able to learn continuous-valued latent representations for parallel sentences. Experiments on both intrinsic and extrinsic evaluations on statistical machine translation tasks show that our autoencoder achieves substantial improvements over the baselines.

pdf bib
Active Learning for Dependency Parsing with Partial Annotation
Zhenghua Li | Min Zhang | Yue Zhang | Zhanyi Liu | Wenliang Chen | Hua Wu | Haifeng Wang
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Finding Arguments as Sequence Labeling in Discourse Parsing
Ziwei Fan | Zhenghua Li | Min Zhang
Proceedings of the CoNLL-16 shared task

2015

pdf bib
Learning bilingual distributed phrase represenations for statistical machine translation
Chaochao Wang | Deyi Xiong | Min Zhang | Chunyu Kit
Proceedings of Machine Translation Summit XV: Papers

pdf bib
Bilingual Correspondence Recursive Autoencoder for Statistical Machine Translation
Jinsong Su | Deyi Xiong | Biao Zhang | Yang Liu | Junfeng Yao | Min Zhang
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Learning Semantic Representations for Nonterminals in Hierarchical Phrase-Based Translation
Xing Wang | Deyi Xiong | Min Zhang
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Document-Level Machine Translation Evaluation with Gist Consistency and Text Cohesion
Zhengxian Gong | Min Zhang | Guodong Zhou
Proceedings of the Second Workshop on Discourse in Machine Translation

pdf bib
Proceedings of the Fifth Named Entity Workshop
Xiangyu Duan | Rafael E. Banchs | Min Zhang | Haizhou Li | A Kumaran
Proceedings of the Fifth Named Entity Workshop

pdf bib
Whitepaper of NEWS 2015 Shared Task on Machine Transliteration
Min Zhang | Haizhou Li | Rafael E. Banchs | A Kumaran
Proceedings of the Fifth Named Entity Workshop

pdf bib
Report of NEWS 2015 Machine Transliteration Shared Task
Rafael E. Banchs | Min Zhang | Xiangyu Duan | Haizhou Li | A. Kumaran
Proceedings of the Fifth Named Entity Workshop

pdf bib
A Context-Aware Topic Model for Statistical Machine Translation
Jinsong Su | Deyi Xiong | Yang Liu | Xianpei Han | Hongyu Lin | Junfeng Yao | Min Zhang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf bib
Coupled Sequence Labeling on Heterogeneous Annotations: POS Tagging as a Case Study
Zhenghua Li | Jiayuan Chao | Min Zhang | Wenliang Chen
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf bib
Word Sense Induction for Machine Translation
Min Zhang
Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing

pdf bib
Proceedings of the Third CIPS-SIGHAN Joint Conference on Chinese Language Processing
Le Sun | Chengqing Zong | Min Zhang | Gina-Anne Levow
Proceedings of the Third CIPS-SIGHAN Joint Conference on Chinese Language Processing

pdf bib
Ambiguity-aware Ensemble Training for Semi-supervised Dependency Parsing
Zhenghua Li | Min Zhang | Wenliang Chen
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
A Sense-Based Translation Model for Statistical Machine Translation
Deyi Xiong | Min Zhang
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Semantics, Discourse and Statistical Machine Translation
Deyi Xiong | Min Zhang
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: Tutorials

pdf bib
Soft Cross-lingual Syntax Projection for Dependency Parsing
Zhenghua Li | Min Zhang | Wenliang Chen
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
Feature Embedding for Dependency Parsing
Wenliang Chen | Yue Zhang | Min Zhang
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
Synchronous Constituent Context Model for Inducing Bilingual Synchronous Structures
Xiangyu Duan | Min Zhang | Qiaoming Zhu
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
Dependency Parsing: Past, Present, and Future
Wenliang Chen | Zhenghua Li | Min Zhang
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Tutorial Abstracts

2013

pdf bib
Semi-Supervised Feature Transformation for Dependency Parsing
Wenliang Chen | Min Zhang | Yue Zhang
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Lexical Chain Based Cohesion Models for Document-Level Statistical Machine Translation
Deyi Xiong | Yang Ding | Min Zhang | Chew Lim Tan
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Fast and Accurate Shift-Reduce Constituent Parsing
Muhua Zhu | Yue Zhang | Wenliang Chen | Min Zhang | Jingbo Zhu
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Feature-Rich Segment-Based News Event Detection on Twitter
Yanxia Qin | Yue Zhang | Min Zhang | Dequan Zheng
Proceedings of the Sixth International Joint Conference on Natural Language Processing

2012

pdf bib
Utilizing Dependency Language Models for Graph-based Dependency Parsing Models
Wenliang Chen | Min Zhang | Haizhou Li
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
A Topic Similarity Model for Hierarchical Phrase-based Translation
Xinyan Xiao | Deyi Xiong | Min Zhang | Qun Liu | Shouxun Lin
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Modeling the Translation of Predicate-Argument Structure for SMT
Deyi Xiong | Min Zhang | Haizhou Li
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Proceedings of the ACL 2012 System Demonstrations
Min Zhang
Proceedings of the ACL 2012 System Demonstrations

pdf bib
Improved Constituent Context Model with Features
Yun Huang | Min Zhang | Chew Lim Tan
Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation

pdf bib
Proceedings of the 4th Named Entity Workshop (NEWS) 2012
Min Zhang | Haizhou Li | A Kumaran
Proceedings of the 4th Named Entity Workshop (NEWS) 2012

pdf bib
Whitepaper of NEWS 2012 Shared Task on Machine Transliteration
Min Zhang | Haizhou Li | A Kumaran | Ming Liu
Proceedings of the 4th Named Entity Workshop (NEWS) 2012

pdf bib
Report of NEWS 2012 Machine Transliteration Shared Task
Min Zhang | Haizhou Li | A Kumaran | Ming Liu
Proceedings of the 4th Named Entity Workshop (NEWS) 2012

pdf bib
Improved Combinatory Categorial Grammar Induction with Boundary Words and Bayesian Inference
Yun Huang | Min Zhang | Chew-Lim Tan
Proceedings of COLING 2012

pdf bib
A Separately Passive-Aggressive Training Algorithm for Joint POS Tagging and Dependency Parsing
Zhenghua Li | Min Zhang | Wanxiang Che | Ting Liu
Proceedings of COLING 2012

pdf bib
Classifier-Based Tense Model for SMT
ZhengXian Gong | Min Zhang | ChewLim Tan | GuoDong Zhou
Proceedings of COLING 2012: Posters

pdf bib
N-gram-based Tense Models for Statistical Machine Translation
Zhengxian Gong | Min Zhang | Chew Lim Tan | Guodong Zhou
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

2011

pdf bib
Enhancing Language Models in Statistical Machine Translation with Backward N-grams and Mutual Information Triggers
Deyi Xiong | Min Zhang | Haizhou Li
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Nonparametric Bayesian Machine Transliteration with Synchronous Adaptor Grammars
Yun Huang | Min Zhang | Chew Lim Tan
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Proceedings of the 3rd Named Entities Workshop (NEWS 2011)
Min Zhang | Haizhou Li | A Kumaran
Proceedings of the 3rd Named Entities Workshop (NEWS 2011)

pdf bib
Report of NEWS 2011 Machine Transliteration Shared Task
Min Zhang | Haizhou Li | A Kumaran | Ming Liu
Proceedings of the 3rd Named Entities Workshop (NEWS 2011)

pdf bib
Whitepaper of NEWS 2011 Shared Task on Machine Transliteration
Min Zhang | A Kumaran | Haizhou Li
Proceedings of the 3rd Named Entities Workshop (NEWS 2011)

pdf bib
CLGVSM: Adapting Generalized Vector Space Model to Cross-lingual Document Clustering
Guoyu Tang | Yunqing Xia | Min Zhang | Haizhou Li | Fang Zheng
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
Joint Alignment and Artificial Data Generation: An Empirical Study of Pivot-based Machine Transliteration
Min Zhang | Xiangyu Duan | Ming Liu | Yunqing Xia | Haizhou Li
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
SMT Helps Bitext Dependency Parsing
Wenliang Chen | Jun’ichi Kazama | Min Zhang | Yoshimasa Tsuruoka | Yujie Zhang | Yiou Wang | Kentaro Torisawa | Haizhou Li
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

pdf bib
Cache-based Document-level Statistical Machine Translation
Zhengxian Gong | Min Zhang | Guodong Zhou
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

pdf bib
Joint Models for Chinese POS Tagging and Dependency Parsing
Zhenghua Li | Min Zhang | Wanxiang Che | Ting Liu | Wenliang Chen | Haizhou Li
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

2010

pdf bib
Pseudo-Word for Phrase-Based Machine Translation
Xiangyu Duan | Min Zhang | Haizhou Li
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Exploring Syntactic Structural Features for Sub-Tree Alignment Using Bilingual Tree Kernels
Jun Sun | Min Zhang | Chew Lim Tan
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Error Detection for Statistical Machine Translation Using Linguistic Features
Deyi Xiong | Min Zhang | Haizhou Li
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Convolution Kernel over Packed Parse Forest
Min Zhang | Hui Zhang | Haizhou Li
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Non-Isomorphic Forest Pair Translation
Hui Zhang | Min Zhang | Haizhou Li | Eng Siong Chng
Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing

pdf bib
Learning Translation Boundaries for Phrase-Based Decoding
Deyi Xiong | Min Zhang | Haizhou Li
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

pdf bib
I2R’s machine translation system for IWSLT 2010
Xiangyu Duan | Rafael Banchs | Jun Lang | Deyi Xiong | Aiti Aw | Min Zhang | Haizhou Li
Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign

pdf bib
Report of NEWS 2010 Transliteration Generation Shared Task
Haizhou Li | A Kumaran | Min Zhang | Vladimir Pervouchine
Proceedings of the 2010 Named Entities Workshop

pdf bib
Whitepaper of NEWS 2010 Shared Task on Transliteration Generation
Haizhou Li | A Kumaran | Min Zhang | Vladimir Pervouchine
Proceedings of the 2010 Named Entities Workshop

pdf bib
Proceedings of the 4th Workshop on Cross Lingual Information Access
Sudeshna Sarkar | Min Zhang | Adam Lopez | Raghavendra Udupa
Proceedings of the 4th Workshop on Cross Lingual Information Access

pdf bib
Linguistically Annotated Reordering: Evaluation and Analysis
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Computational Linguistics, Volume 36, Issue 3 - September 2010

pdf bib
Book Review: Introduction to Chinese Natural Language Processing by Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang
Min Zhang
Computational Linguistics, Volume 36, Issue 4 - December 2010

pdf bib
Discriminative Induction of Sub-Tree Alignment using Limited Labeled Data
Jun Sun | Min Zhang | Chew Lim Tan
Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)

pdf bib
EM-based Hybrid Model for Bilingual Terminology Extraction from Comparable Corpora
Lianhau Lee | Aiti Aw | Min Zhang | Haizhou Li
Coling 2010: Posters

pdf bib
Head-modifier Relation based Non-lexical Reordering Model for Phrase-Based Translation
Shui Liu | Sheng Li | Tiejun Zhao | Min Zhang | Pengyuan Liu
Coling 2010: Posters

pdf bib
Improving Name Origin Recognition with Context Features and Unlabelled Data
Vladimir Pervouchine | Min Zhang | Ming Liu | Haizhou Li
Coling 2010: Posters

pdf bib
Machine Transliteration: Leveraging on Third Languages
Min Zhang | Xiangyu Duan | Vladimir Pervouchine | Haizhou Li
Coling 2010: Posters

2009

pdf bib
I2R’s machine translation system for IWSLT 2009
Xiangyu Duan | Deyi Xiong | Hui Zhang | Min Zhang | Haizhou Li
Proceedings of the 6th International Workshop on Spoken Language Translation: Evaluation Campaign

In this paper, we describe the system and approach used by the Institute for Infocomm Research (I2R) for the IWSLT 2009 spoken language translation evaluation campaign. Two kinds of machine translation systems are applied, namely, phrase-based machine translation system and syntax-based machine translation system. To test syntax-based machine translation system on spoken language translation, variational systems are explored. On top of both phrase-based and syntax-based single systems, we further use rescoring method to improve the individual system performance and use system combination method to combine the strengths of the different individual systems. Rescoring is applied on each single system output, and system combination is applied on all rescoring outputs. Finally, our system combination framework shows better performance in Chinese-English BTEC task.

pdf bib
Feature-Based Method for Document Alignment in Comparable News Corpora
Thuy Vu | Ai Ti Aw | Min Zhang
Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009)

pdf bib
Tree Kernel-based SVM with Structured Syntactic Knowledge for BTG-based Phrase Reordering
Min Zhang | Haizhou Li
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf bib
Fast Translation Rule Matching for Syntax-based Statistical Machine Translation
Hui Zhang | Min Zhang | Haizhou Li | Chew Lim Tan
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf bib
K-Best Combination of Syntactic Parsers
Hui Zhang | Min Zhang | Chew Lim Tan | Haizhou Li
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf bib
Report of NEWS 2009 Machine Transliteration Shared Task
Haizhou Li | A Kumaran | Vladimir Pervouchine | Min Zhang
Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration (NEWS 2009)

pdf bib
Whitepaper of NEWS 2009 Machine Transliteration Shared Task
Haizhou Li | A Kumaran | Min Zhang | Vladimir Pervouchine
Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration (NEWS 2009)

pdf bib
Forest-based Tree Sequence to String Translation Model
Hui Zhang | Min Zhang | Haizhou Li | Aiti Aw | Chew Lim Tan
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
A Syntax-Driven Bracketing Model for Phrase-Based Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
A non-contiguous Tree Sequence Alignment-based Model for Statistical Machine Translation
Jun Sun | Min Zhang | Chew Lim Tan
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
A Comparative Study of Hypothesis Alignment and its Improvement for Machine Translation System Combination
Boxing Chen | Min Zhang | Haizhou Li | Aiti Aw
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
MARS: Multilingual Access and Retrieval System with Enhanced Query Translation and Document Retrieval
Lianhau Lee | Aiti Aw | Thuy Vu | Sharifah Aljunied Mahani | Min Zhang | Haizhou Li
Proceedings of the ACL-IJCNLP 2009 Software Demonstrations

pdf bib
Efficient Beam Thresholding for Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of Machine Translation Summit XII: Posters

pdf bib
A Source Dependency Model for Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of Machine Translation Summit XII: Posters

2008

pdf bib
A Tree Sequence Alignment-based Tree-to-Tree Translation Model
Min Zhang | Hongfei Jiang | Aiti Aw | Haizhou Li | Chew Lim Tan | Sheng Li
Proceedings of ACL-08: HLT

pdf bib
A Linguistically Annotated Reordering Model for BTG-based Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of ACL-08: HLT, Short Papers

pdf bib
Exploiting N-best Hypotheses for SMT Self-Enhancement
Boxing Chen | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of ACL-08: HLT, Short Papers

pdf bib
Name Origin Recognition Using Maximum Entropy Model and Diverse Features
Min Zhang | Chengjie Sun | Haizhou Li | AiTi Aw | Chew Lim Tan | Xiaolong Wang
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

pdf bib
Identify Temporal Websites Based on User Behavior Analysis
Yong Wang | Yiqun Liu | Min Zhang | Shaoping Ma | Liyun Ru
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

pdf bib
Refinements in BTG-based Statistical Machine Translation
Deyi Xiong | Min Zhang | AiTi Aw | Haitao Mi | Qun Liu | Shouxun Lin
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

pdf bib
Term Extraction Through Unithood and Termhood Unification
Thuy Vu | Ai Ti Aw | Min Zhang
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-II

pdf bib
Fast Computing Grammar-driven Convolution Tree Kernel for Semantic Role Labeling
Wanxiang Che | Min Zhang | Ai Ti Aw | Chew Lim Tan | Ting Liu | Sheng Li
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-II

pdf bib
Regenerating Hypotheses for Statistical Machine Translation
Boxing Chen | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
Linguistically Annotated BTG for Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
Grammar Comparison Study for Translational Equivalence Modeling and Statistical Machine Translation
Min Zhang | Hongfei Jiang | Haizhou Li | Aiti Aw | Sheng Li
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
I2R multi-pass machine translation system for IWSLT 2008.
Boxing Chen | Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign

In this paper, we describe the system and approach used by the Institute for Infocomm Research (I2R) for the IWSLT 2008 spoken language translation evaluation campaign. In the system, we integrate various decoding algorithms into a multi-pass translation framework. The multi-pass approach enables us to utilize various decoding algorithm and to explore much more hypotheses. This paper reports our design philosophy, overall architecture, each individual system and various system combination methods that we have explored. The performance on development and test sets are reported in detail in the paper. The system has shown competitive performance with respect to the BLEU and METEOR measures in Chinese-English Challenge and BTEC tasks.

pdf bib
The TALP&I2R SMT systems for IWSLT 2008.
Maxim Khalilov | Maria R. Costa-jussà | Carlos A. Henríquez Q. | José A. R. Fonollosa | Adolfo Hernández H. | José B. Mariño | Rafael E. Banchs | Chen Boxing | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper gives a description of the statistical machine translation (SMT) systems developed at the TALP Research Center of the UPC (Universitat Polite`cnica de Catalunya) for our participation in the IWSLT’08 evaluation campaign. We present Ngram-based (TALPtuples) and phrase-based (TALPphrases) SMT systems. The paper explains the 2008 systems’ architecture and outlines translation schemes we have used, mainly focusing on the new techniques that are challenged to improve speech-to-speech translation quality. The novelties we have introduced are: improved reordering method, linear combination of translation and reordering models and new technique dealing with punctuation marks insertion for a phrase-based SMT system. This year we focus on the Arabic-English, Chinese-Spanish and pivot Chinese-(English)-Spanish translation tasks.

2007

pdf bib
A Grammar-driven Convolution Tree Kernel for Semantic Role Classification
Min Zhang | Wanxiang Che | Aiti Aw | Chew Lim Tan | Guodong Zhou | Ting Liu | Sheng Li
Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics

pdf bib
A tree-to-tree alignment-based model for statistical machine translation
Min Zhang | Hongfei Jiang | Ai Ti Aw | Jun Sun | Sheng Li | Chew Lim Tan
Proceedings of Machine Translation Summit XI: Papers

pdf bib
Tree Kernel-Based Relation Extraction with Context-Sensitive Structured Parse Tree Information
GuoDong Zhou | Min Zhang | Dong Hong Ji | QiaoMing Zhu
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

pdf bib
I2R Chinese-English translation system for IWSLT 2007
Boxing Chen | Jun Sun | Hongfei Jiang | Min Zhang | Ai Ti Aw
Proceedings of the Fourth International Workshop on Spoken Language Translation

In this paper, we describe the system and approach used by Institute for Infocomm Research (I2R) for the IWSLT 2007 spoken language evaluation campaign. A multi-pass approach is exploited to generate and select best translation. First, we use two decoders namely the open source Moses and an in-home syntax-based decoder to generate N-best lists. Next we spawn new translation entries through a word-based n-gram language model estimated on the former N-best entries. Finally, we join the N-best lists from the previous two passes, and select the best translation by rescoring them with additional feature functions. In particular, this paper reports our effort on new translation entry generation and system combination. The performance on development and test sets are reported. The system was ranked first with respect to the BLEU measure in Chinese-to-English open data track.

2006

pdf bib
Modeling Commonality among Related Classes in Relation Extraction
GuoDong Zhou | Jian Su | Min Zhang
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
A Composite Kernel to Extract Relations between Entities with Both Flat and Structured Features
Min Zhang | Jie Zhang | Jian Su | GuoDong Zhou
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
A Phrase-Based Statistical Model for SMS Text Normalization
AiTi Aw | Min Zhang | Juan Xiao | Jian Su
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

pdf bib
A Hybrid Convolution Tree Kernel for Semantic Role Labeling
Wanxiang Che | Min Zhang | Ting Liu | Sheng Li
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

pdf bib
Exploring Syntactic Features for Relation Extraction using a Convolution Tree Kernel
Min Zhang | Jie Zhang | Jian Su
Proceedings of the Human Language Technology Conference of the NAACL, Main Conference

pdf bib
Chinese Word Segmentation and Named Entity Recognition Based on a Context-Dependent Mutual Information Independence Model
Min Zhang | GuoDong Zhou | LingPeng Yang | DongHong Ji
Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing

2005

pdf bib
Discovering Relations Between Named Entities from a Large Raw Corpus Using Tree Similarity-Based Clustering
Min Zhang | Jian Su | Danmei Wang | Guodong Zhou | Chew Lim Tan
Second International Joint Conference on Natural Language Processing: Full Papers

pdf bib
Phrase-Based Statistical Machine Translation: A Level of Detail Approach
Hendra Setiawan | Haizhou Li | Min Zhang | Beng Chin Ooi
Second International Joint Conference on Natural Language Processing: Full Papers

pdf bib
A Phrase-Based Context-Dependent Joint Probability Model for Named Entity Translation
Min Zhang | Haizhou Li | Jian Su | Hendra Setiawan
Second International Joint Conference on Natural Language Processing: Full Papers

pdf bib
Learning Phrase Translation using Level of Detail Approach
Hendra Setiawan | Haizhou Li | Min Zhang
Proceedings of Machine Translation Summit X: Papers

We propose a simplified Level Of Detail (LOD) algorithm to learn phrase translation for statistical machine translation. In particular, LOD learns unknown phrase translations from parallel texts without linguistic knowledge. LOD uses an agglomerative method to attack the combinatorial explosion that results when generating candidate phrase translations. Although LOD was previously proposed by (Setiawan et al., 2005), we improve the original algorithm in two ways: simplifying the algorithm and using a simpler translation model. Experimental results show that our algorithm provides comparable performance while demonstrating a significant reduction in computation time.

pdf bib
Exploring Various Knowledge in Relation Extraction
GuoDong Zhou | Jian Su | Jie Zhang | Min Zhang
Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05)

2004

pdf bib
A Joint Source-Channel Model for Machine Transliteration
Haizhou Li | Min Zhang | Jian Su
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

pdf bib
Direct Orthographical Mapping for Machine Transliteration
Min Zhang | Haizhou Li | Jian Su
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

2002

pdf bib
Self-Organizing Chinese and Japanese Semantic Maps
Qing Ma | Min Zhang | Masaki Murata | Ming Zhou | Hitoshi Isahara
COLING 2002: The 19th International Conference on Computational Linguistics

pdf bib
Improving Language Model Size Reduction using Better Pruning Criteria
Jianfeng Gao | Min Zhang
Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics

1999

pdf bib
A pipelined multi-engine approach to Chinese-to-Korean machine translation: MATES/CK
Min Zhang | Key-Sun Choi
Proceedings of Machine Translation Summit VII

This paper presents MATES/CK, a Chinese-to-Korean machine translation system. We introduce the design philosophy, component modules, implementation and some other aspects of MATES/CK system in this paper.

pdf bib
Pipelined multi-engine Machine Translation: accomplishment of MATES/CK system
Min Zhang | Key-Sun Choi
Proceedings of the 8th Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages

Search
Co-authors