Xiang Li


pdf bib
When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario
Chengcheng Han | Liqing Cui | Renyu Zhu | Jianing Wang | Nuo Chen | Qiushi Sun | Xiang Li | Ming Gao
Findings of the Association for Computational Linguistics: ACL 2023

Large pre-trained language models (PLMs) have garnered significant attention for their versatility and potential for solving a wide spectrum of natural language processing (NLP) tasks. However, the cost of running these PLMs may be prohibitive. Furthermore, PLMs may not be open-sourced due to commercial considerations and potential risks of misuse, such as GPT-3. The parameters and gradients of PLMs are unavailable in this scenario. To solve the issue, black-box tuning has been proposed, which utilizes derivative-free optimization (DFO), instead of gradient descent, for training task-specific continuous prompts. However, these gradient-free methods still exhibit a significant gap compared to gradient-based methods. In this paper, we introduce gradient descent into black-box tuning scenario through knowledge distillation. Furthermore, we propose a novel method GDFO, which integrates gradient descent and derivative-free optimization to optimize task-specific continuous prompts in a harmonized manner. Experimental results show that GDFO can achieve significant performance gains over previous state-of-the-art methods.

pdf bib
Pass-Tuning: Towards Structure-Aware Parameter-Efficient Tuning for Code Representation Learning
Nuo Chen | Qiushi Sun | Jianing Wang | Xiang Li | Ming Gao
Findings of the Association for Computational Linguistics: EMNLP 2023

Code pre-trained models (CodePTMs) have recently become the de-facto paradigm for various tasks in the domain of code intelligence. To achieve excellent performance, the widely used strategy is to fine-tune all the parameters of CodePTMs. However, as the model size increases along with the number of downstream tasks, this strategy becomes excessively expensive. There are also some prior works that utilize Parameter-Efficient Learning (PEL) methods for model tuning in natural language processing to mitigate similar problems, but applying them directly to CodePTMs fails to capture the inherent structural characteristics of codes. To address the problem, in this paper, we propose Pass-Tuning for structure-aware Parameter-Efficient code representation learning. Specifically, a plug-and-play graph neural network module that can learn from Abstract Syntax Tree (AST) is employed as a tunable prefix. On the one hand, Pass-Tuning can further exploit the structural information of source code. On the other hand, it could serve as a replacement for full fine-tuning. We evaluate our method on multiple tasks across eight programming languages, including code understanding and generation. These results demonstrate the effectiveness, robustness, and universality of our method.

pdf bib
Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding
Jianing Wang | Qiushi Sun | Nuo Chen | Chengyu Wang | Jun Huang | Ming Gao | Xiang Li
Findings of the Association for Computational Linguistics: EMNLP 2023

The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the predominant semi-supervised learning (SSL) approaches, which utilizes large-scale unlabeled data to generate synthetic examples. However, too many noisy labels will hurt the model performance, and the self-training procedure requires multiple training iterations making it more expensive if all the model parameters of the PLM are updated. This paper presents UPET, a novel Uncertainty-aware Parameter-Efficient self-Training framework to effectively and efficiently address the labeled data scarcity issue. Specifically, we incorporate Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation for the teacher model and then judiciously select reliable pseudo-labeled examples based on confidence and certainty. During the student training, we introduce multiple parameter-efficient learning (PEL) paradigms that allow optimizes only a small percentage of parameters. We also propose a novel Easy-Hard Contrastive Tuning to enhance the robustness and generalization. Extensive experiments over multiple downstream tasks demonstrate that UPET achieves a substantial improvement in terms of performance and efficiency. Our codes and data are released at https: //github.com/wjn1996/UPET.

pdf bib
Evaluating and Enhancing the Robustness of Code Pre-trained Models through Structure-Aware Adversarial Samples Generation
Nuo Chen | Qiushi Sun | Jianing Wang | Ming Gao | Xiaoli Li | Xiang Li
Findings of the Association for Computational Linguistics: EMNLP 2023

Code pre-trained models (CodePTMs) have significantly advanced the field of neural code intelligence. Despite their capabilities, these models are susceptible to adversarial attacks that subtly modify the model inputs, resulting in incorrect outputs or predictions. Previous methods of robustness evaluation for CodePTMs primarily stem from a textual perspective, without explicitly taking into account the structure of the code. Furthermore, prior studies fail to encompass a broad enough spectrum of tasks and models. In this paper, we propose a set of novel robustness evaluation methods based on the intrinsic structure of the code. Specifically, we first launch adversarial attacks on crucial identifier tokens and sub-tree structures to explore the impact of imperceptible perturbation. Then, we perform global restructuring of the code using different traversal methods for abstract syntax trees, aiming to explore the model’s sensitivity to input samples with equivalent information. Moreover, for each scenario, we employ adversarial training methods to explore the possibility of restoring the performance of perturbed models. For both code understanding and generation, our proposed method has demonstrated its effectiveness across a wide range of models and tasks, thereby allowing us to make one step forward in our understanding of the inner mechanisms of CodePTMs.

pdf bib
In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model
Yanzhi Tian | Xiang Li | Zeming Liu | Yuhang Guo | Bin Wang
Findings of the Association for Computational Linguistics: EMNLP 2023

In-Image Machine Translation (IIMT) aims to convert images containing texts from one language to another. Traditional approaches for this task are cascade methods, which utilize optical character recognition (OCR) followed by neural machine translation (NMT) and text rendering. However, the cascade methods suffer from compounding errors of OCR and NMT, leading to a decrease in translation quality. In this paper, we propose an end-to-end model instead of the OCR, NMT and text rendering pipeline. Our neural architecture adopts encoder-decoder paradigm with segmented pixel sequences as inputs and outputs. Through end-to-end training, our model yields improvements across various dimensions, (i) it achieves higher translation quality by avoiding error propagation, (ii) it demonstrates robustness for out domain data, and (iii) it displays insensitivity to incomplete words. To validate the effectiveness of our method and support for future research, we construct our dataset containing 4M pairs of De-En images and train our end-to-end model. The experimental results show that our approach outperforms both cascade method and current end-to-end model.

pdf bib
Multi-Target Semantic Parsing with Collaborative Deliberation Network
Xiang Li | Fangyu Lei | Shizhu He | Kang Liu | Jun Zhao
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

pdf bib
The Xiaomi AI Lab’s Speech Translation Systems for IWSLT 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task
Wuwei Huang | Mengge Liu | Xiang Li | Yanzhi Tian | Fengyu Yang | Wen Zhang | Jian Luan | Bin Wang | Yuhang Guo | Jinsong Su
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)

This system description paper introduces the systems submitted by Xiaomi AI Lab to the three tracks of the IWSLT 2023 Evaluation Campaign, namely the offline speech translation (Offline-ST) track, the offline speech-to-speech translation (Offline-S2ST) track, and the simultaneous speech translation (Simul-ST) track. All our submissions for these three tracks only involve the English-Chinese language direction. Our English-Chinese speech translation systems are constructed using large-scale pre-trained models as the foundation. Specifically, we fine-tune these models’ corresponding components for various downstream speech translation tasks. Moreover, we implement several popular techniques, such as data filtering, data augmentation, speech segmentation, and model ensemble, to improve the system’s overall performance. Extensive experiments show that our systems achieve a significant improvement over the strong baseline systems in terms of the automatic evaluation metric.

pdf bib
Towards Noise-Tolerant Speech-Referring Video Object Segmentation: Bridging Speech and Text
Xiang Li | Jinglu Wang | Xiaohao Xu | Muqiao Yang | Fan Yang | Yizhou Zhao | Rita Singh | Bhiksha Raj
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Linguistic communication is prevalent in Human-Computer Interaction (HCI). Speech (spoken language) serves as a convenient yet potentially ambiguous form due to noise and accents, exposing a gap compared to text. In this study, we investigate the prominent HCI task, Referring Video Object Segmentation (R-VOS), which aims to segment and track objects using linguistic references. While text input is well-investigated, speech input is under-explored. Our objective is to bridge the gap between speech and text, enabling the adaptation of existing text-input R-VOS models to accommodate noisy speech input effectively. Specifically, we propose a method to align the semantic spaces between speech and text by incorporating two key modules: 1) Noise-Aware Semantic Adjustment (NSA) for clear semantics extraction from noisy speech; and 2) Semantic Jitter Suppression (SJS) enabling R-VOS models to tolerate noisy queries. Comprehensive experiments conducted on the challenging AVOS benchmarks reveal that our proposed method outperforms state-of-the-art approaches.

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
OssCSE: Overcoming Surface Structure Bias in Contrastive Learning for Unsupervised Sentence Embedding
Zhan Shi | Guoyin Wang | Ke Bai | Jiwei Li | Xiang Li | Qingjun Cui | Belinda Zeng | Trishul Chilimbi | Xiaodan Zhu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Contrastive learning has been demonstrated effective in unsupervised sentence representation learning. Given one sentence, positive pairs are obtained by passing the sentence to the encoder twice using the different dropout masks, and negative pairs are obtained by taking another sentence in the same mini-batch. However, the method suffers from the surface structure bias, i.e., sentences with similar surface structures will be regarded as close in semantics while sentences with dissimilar surface structures will be viewed as distinct in semantics. This leads to the result that paraphrasing a sentence that is dissimilar in surface structure will receive a lower semantic similarity score than inserting a negative word into the sentence. In this paper, we first verify the bias by collecting a sentence transformation testset. Then we systematically probe the existing models by proposing novel splits based on benchmark datasets in accordance with semantic and surface structure similarity. We tackle the bias in two aspects: balancing the learning target by augmenting with data that counters the bias, and meanwhile preserving word semantics by leveraging recall loss to prevent catastrophic forgetting. We evaluate our model on standard semantic textual similarity (STS) tasks using different pre-trained backbones and achieve state-of-the-art averaged performance across the STS benchmarks. Particularly, our models that are fine-tuned with RoBERTabase and RoBERTalarge achieve significantly better performance on most benchmark datasets.

pdf bib
DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models
Chengcheng Han | Xiaowei Du | Che Zhang | Yixin Lian | Xiang Li | Ming Gao | Baoyuan Wang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Chain-of-Thought (CoT) prompting has successfully enhanced the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters. However, it is ineffective, or even detrimental, to the performance on reasoning tasks in Smaller Language Models (SLMs) with less than 10 billion parameters. In this paper, we propose Dialogue-guided Chain-of-Thought (DialCoT) to improve the reasoning capabilities of SLMs, with the aim of generating intermediate reasoning steps in a dialogue format to guide the model to the final answer. Furthermore, we optimize the model to choose the optimal reasoning path through the Proximal Policy Optimization (PPO) algorithm, further enhancing its reasoning capabilities. Compared to previous methods, our advantages lie in: 1) We transform the process of solving complex reasoning problems into decomposing problems and solving a series of simpler sub-questions, significantly reducing task difficulty and making it more suitable for SLMs. 2) We optimize the model to choose the optimal reasoning path through the PPO algorithm. Comprehensive experiments on four arithmetic reasoning datasets show that our method can achieve significant performance gains over state-of-the-art competitors.

pdf bib
Editing Common Sense in Transformers
Anshita Gupta | Debanjan Mondal | Akshay Sheshadri | Wenlong Zhao | Xiang Li | Sarah Wiegreffe | Niket Tandon
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Editing model parameters directly in Transformers makes updating open-source transformer-based models possible without re-training. However, these editing methods have only been evaluated on statements about encyclopedic knowledge with a single correct answer. Commonsense knowledge with multiple correct answers, e.g., an apple can be green or red but not transparent, has not been studied but is as essential for enhancing transformers’ reliability and usefulness. In this paper, we investigate whether commonsense judgments are causally associated with localized, editable parameters in Transformers, and we provide an affirmative answer. We find that directly applying the MEMIT editing algorithm results in sub-par performance and improve it for the commonsense domain by varying edit tokens and improving the layer selection strategy, i.e., MEMITCSK. GPT-2 Large and XL models edited using MEMITCSK outperform best-fine-tuned baselines by 10.97% and 10.73% F1 scores on PEP3k and 20Q datasets. In addition, we propose a novel evaluation dataset, PROBE\ SET, that contains unaffected and affected neighborhoods, affected paraphrases, and affected reasoning challenges. MEMITCSK performs well across the metrics while fine-tuning baselines show significant trade-offs between unaffected and affected metrics. These results suggest a compelling future direction for incorporating feedback about common sense into Transformers through direct model editing.

pdf bib
Exploring Better Text Image Translation with Multimodal Codebook
Zhibin Lan | Jiawei Yu | Xiang Li | Wen Zhang | Jian Luan | Bin Wang | Degen Huang | Jinsong Su
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a cascaded manner, which tends to suffer from the error propagation of optical character recognition (OCR). In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propose a TIT model with a multimodal codebook, which is able to associate the image with relevant texts, providing useful supplementary information for translation. Moreover, we present a multi-stage training framework involving text machine translation, image-text alignment, and TIT tasks, which fully exploits additional bilingual texts, OCR dataset and our OCRMT30K dataset to train our model. Extensive experiments and in-depth analyses strongly demonstrate the effectiveness of our proposed model and training framework.

pdf bib
Ranking-Enhanced Unsupervised Sentence Representation Learning
Yeon Seonwoo | Guoyin Wang | Changmin Seo | Sajal Choudhary | Jiwei Li | Xiang Li | Puyang Xu | Sunghyun Park | Alice Oh
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Unsupervised sentence representation learning has progressed through contrastive learning and data augmentation methods such as dropout masking. Despite this progress, sentence encoders are still limited to using only an input sentence when predicting its semantic vector. In this work, we show that the semantic meaning of a sentence is also determined by nearest-neighbor sentences that are similar to the input sentence. Based on this finding, we propose a novel unsupervised sentence encoder, RankEncoder. RankEncoder predicts the semantic vector of an input sentence by leveraging its relationship with other sentences in an external corpus, as well as the input sentence itself. We evaluate RankEncoder on semantic textual benchmark datasets. From the experimental results, we verify that 1) RankEncoder achieves 80.07% Spearman’s correlation, a 1.1% absolute improvement compared to the previous state-of-the-art performance, 2) RankEncoder is universally applicable to existing unsupervised sentence embedding methods, and 3) RankEncoder is specifically effective for predicting the similarity scores of similar sentence pairs.

pdf bib
S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering
Fangyu Lei | Xiang Li | Yifan Wei | Shizhu He | Yiming Huang | Jun Zhao | Kang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Answering multi-hop questions over hybrid factual knowledge from the given text and table (TextTableQA) is a challenging task. Existing models mainly adopt a retriever-reader framework, which have several deficiencies, such as noisy labeling in training retriever, insufficient utilization of heterogeneous information over text and table, and deficient ability for different reasoning operations. In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner. We use a retriever with refinement training to solve the noisy labeling problem. Then, a hybrid selector considers the linked relationships between heterogeneous data to select the most relevant factual knowledge. For the final stage, instead of adapting a reading comprehension module like in previous methods, we employ a generation-based reasoner to obtain answers. This includes two approaches: a row-wise generator and an LLM prompting generator (first time used in this task). The experimental results demonstrate that our method achieves competitive results in the few-shot setting. When trained on the full dataset, our approach outperforms all baseline methods, ranking first on the HybridQA leaderboard.


pdf bib
The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022
Bao Guo | Mengge Liu | Wen Zhang | Hexuan Chen | Chang Mu | Xiang Li | Jianwei Cui | Bin Wang | Yuhang Guo
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

This system paper describes the Xiaomi Translation System for the IWSLT 2022 Simultaneous Speech Translation (noted as SST) shared task. We participate in the English-to-Mandarin Chinese Text-to-Text (noted as T2T) track. Our system is built based on the Transformer model with novel techniques borrowed from our recent research work. For the data filtering, language-model-based and rule-based methods are conducted to filter the data to obtain high-quality bilingual parallel corpora. We also strengthen our system with some dominating techniques related to data augmentation, such as knowledge distillation, tagged back-translation, and iterative back-translation. We also incorporate novel training techniques such as R-drop, deep model, and large batch training which have been shown to be beneficial to the naive Transformer model. In the SST scenario, several variations of extttwait-k strategies are explored. Furthermore, in terms of robustness, both data-based and model-based ways are used to reduce the sensitivity of our system to Automatic Speech Recognition (ASR) outputs. We finally design some inference algorithms and use the adaptive-ensemble method based on multiple model variants to further improve the performance of the system. Compared with strong baselines, fusing all techniques can improve our system by 2 extasciitilde3 BLEU scores under different latency regimes.

pdf bib
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection
Bin Liang | Qinglin Zhu | Xiang Li | Min Yang | Lin Gui | Yulan He | Ruifeng Xu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Zero-shot stance detection (ZSSD) aims to detect the stance for an unseen target during the inference stage. In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastive learning and target-aware prototypical graph contrastive learning. Specifically, a stance contrastive learning strategy is employed to better generalize stance features for unseen targets. Further, we build a prototypical graph for each instance to learn the target-based representation, in which the prototypes are deployed as a bridge to share the graph structures between the known targets and the unseen ones. Then a novel target-aware prototypical graph contrastive learning strategy is devised to generalize the reasoning ability of target-based stance representations to the unseen targets. Extensive experiments on three benchmark datasets show that the proposed approach achieves state-of-the-art performance in the ZSSD task.

pdf bib
Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network
Bin Liang | Chenwei Lou | Xiang Li | Min Yang | Lin Gui | Yulan He | Wenjie Pei | Ruifeng Xu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

With the increasing popularity of posting multimodal messages online, many recent studies have been carried out utilizing both textual and visual information for multi-modal sarcasm detection. In this paper, we investigate multi-modal sarcasm detection from a novel perspective by constructing a cross-modal graph for each instance to explicitly draw the ironic relations between textual and visual modalities. Specifically, we first detect the objects paired with descriptions of the image modality, enabling the learning of important visual information. Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance. Furthermore, we devise a cross-modal graph convolutional network to make sense of the incongruity relations between modalities for multi-modal sarcasm detection. Extensive experimental results and in-depth analysis show that our model achieves state-of-the-art performance in multi-modal sarcasm detection.

pdf bib
Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings
Shib Dasgupta | Michael Boratko | Siddhartha Mishra | Shriya Atmakuri | Dhruvesh Patel | Xiang Li | Andrew McCallum
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Learning representations of words in a continuous space is perhaps the most fundamental task in NLP, however words interact in ways much richer than vector dot product similarity can provide. Many relationships between words can be expressed set-theoretically, for example, adjective-noun compounds (eg. “red cars”⊆“cars”) and homographs (eg. “tongue”∩“body” should be similar to “mouth”, while “tongue”∩“language” should be similar to “dialect”) have natural set-theoretic interpretations. Box embeddings are a novel region-based representation which provide the capability to perform these set-theoretic operations. In this work, we provide a fuzzy-set interpretation of box embeddings, and learn box representations of words using a set-theoretic training objective. We demonstrate improved performance on various word similarity tasks, particularly on less common words, and perform a quantitative and qualitative analysis exploring the additional unique expressivity provided by Word2Box.

pdf bib
A Neural Network Architecture for Program Understanding Inspired by Human Behaviors
Renyu Zhu | Lei Yuan | Xiang Li | Ming Gao | Wenyuan Cai
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Program understanding is a fundamental task in program language processing. Despite the success, existing works fail to take human behaviors as reference in understanding programs. In this paper, we consider human behaviors and propose the PGNN-EK model that consists of two main components. On the one hand, inspired by the “divide-and-conquer” reading behaviors of humans, we present a partitioning-based graph neural network model PGNN on the upgraded AST of codes. On the other hand, to characterize human behaviors of resorting to other resources to help code comprehension, we transform raw codes with external knowledge and apply pre-training techniques for information extraction. Finally, we combine the two embeddings generated from the two components to output code embeddings. We conduct extensive experiments to show the superior performance of PGNN-EK on the code summarization and code clone detection tasks. In particular, to show the generalization ability of our model, we release a new dataset that is more challenging for code clone detection and could advance the development of the community. Our codes and data are publicly available at https://github.com/RecklessRonan/PGNN-EK.

pdf bib
Lexical Knowledge Internalization for Neural Dialog Generation
Zhiyong Wu | Wei Bi | Xiang Li | Lingpeng Kong | Ben Kao
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose knowledge internalization (KI), which aims to complement the lexical knowledge into neural dialog models. Instead of further conditioning the knowledge-grounded dialog (KGD) models on externally retrieved knowledge, we seek to integrate knowledge about each input token internally into the model’s parameters. To tackle the challenge due to the large scale of lexical knowledge, we adopt the contrastive learning approach and create an effective token-level lexical knowledge retriever that requires only weak supervision mined from Wikipedia. We demonstrate the effectiveness and general applicability of our approach on various datasets and diversified model structures.

pdf bib
Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder
Fangyu Lei | Shizhu He | Xiang Li | Jun Zhao | Kang Liu
Proceedings of the 29th International Conference on Computational Linguistics

pdf bib
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction
Yequan Wang | Xiang Li | Aixin Sun | Xuying Meng | Huaming Liao | Jiafeng Guo
Proceedings of the 29th International Conference on Computational Linguistics

Quotation extraction aims to extract quotations from written text. There are three components in a quotation: source refers to the holder of the quotation, cue is the trigger word(s), and content is the main body. Existing solutions for quotation extraction mainly utilize rule-based approaches and sequence labeling models. While rule-based approaches often lead to low recalls, sequence labeling models cannot well handle quotations with complicated structures. In this paper, we propose the Context and Former-Label Enhanced Net () for quotation extraction. is able to extract complicated quotations with components of variable lengths and complicated structures. On two public datasets (and ) and one proprietary dataset (), we show that our achieves state-of-the-art performance on complicated quotation extraction.

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
Detecting Relevant Differences Between Similar Legal Texts
Xiang Li | Jiaxun Gao | Diana Inkpen | Wolfgang Alschner
Proceedings of the Natural Legal Language Processing Workshop 2022

Given two similar legal texts, is it useful to be able to focus only on the parts that contain relevant differences. However, because of variation in linguistic structure and terminology, it is not easy to identify true semantic differences. An accurate difference detection model between similar legal texts is therefore in demand, in order to increase the efficiency of legal research and document analysis. In this paper, we automatically label a training dataset of sentence pairs using an existing legal resource of international investment treaties that were already manually annotated with metadata. Then we propose models based on state-of-the-art deep learning techniques for the novel task of detecting relevant differences. In addition to providing solutions for this task, we include models for automatically producing metadata for the treaties that do not have it.

pdf bib
Weakly Supervised Text Classification using Supervision Signals from a Language Model
Ziqian Zeng | Weimin Ni | Tianqing Fang | Xiang Li | Xinran Zhao | Yangqiu Song
Findings of the Association for Computational Linguistics: NAACL 2022

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document itself and “this article is talking about [MASK].” A masked language model can generate words for the [MASK] token. The generated words which summarize the content of a document can be utilized as supervision signals. We propose a latent variable model to learn a word distribution learner which associates generated words to pre-defined categories and a document classifier simultaneously without using any annotated data. Evaluation on three datasets, AGNews, 20Newsgroups, and UCINews, shows that our method can outperform baselines by 2%, 4%, and 3%.

pdf bib
CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure
Nuo Chen | Qiushi Sun | Renyu Zhu | Xiang Li | Xuesong Lu | Ming Gao
Findings of the Association for Computational Linguistics: EMNLP 2022

Code pre-trained models (CodePTMs) have recently demonstrated significant success in code intelligence. To interpret these models, some probing methods have been applied. However, these methods fail to consider the inherent characteristics of codes. In this paper, to address the problem, we propose a novel probing method CAT-probing to quantitatively interpret how CodePTMs attend code structure. We first denoise the input code sequences based on the token types pre-defined by the compilers to filter those tokens whose attention scores are too small. After that, we define a new metric CAT-score to measure the commonality between the token-level attention scores generated in CodePTMs and the pair-wise distances between corresponding AST nodes. The higher the CAT-score, the stronger the ability of CodePTMs to capture code structure. We conduct extensive experiments to integrate CAT-probing with representative CodePTMs for different programming languages. Experimental results show the effectiveness of CAT-probing in CodePTM interpretation. Our codes and data are publicly available at https://github.com/nchen909/CodeAttention.

pdf bib
BIT-Xiaomi’s System for AutoSimTrans 2022
Mengge Liu | Xiang Li | Bao Chen | Yanzhi Tian | Tianwei Lan | Silin Li | Yuhang Guo | Jian Luan | Bin Wang
Proceedings of the Third Workshop on Automatic Simultaneous Translation

This system paper describes the BIT-Xiaomi simultaneous translation system for Autosimtrans 2022 simultaneous translation challenge. We participated in three tracks: the Zh-En text-to-text track, the Zh-En audio-to-text track and the En-Es test-to-text track. In our system, wait-k is employed to train prefix-to-prefix translation models. We integrate streaming chunking to detect boundaries as the source streaming read in. We further improve our system with data selection, data-augmentation and R-drop training methods. Results show that our wait-k implementation outperforms organizer’s baseline by 8 BLEU score at most, and our proposed streaming chunking method further improves about 2 BLEU in low latency regime.

pdf bib
Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)
Antoine Bosselut | Xiang Li | Bill Yuchen Lin | Vered Shwartz | Bodhisattwa Prasad Majumder | Yash Kumar Lal | Rachel Rudinger | Xiang Ren | Niket Tandon | Vilém Zouhar
Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)

pdf bib
Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding
Jianing Wang | Wenkang Huang | Minghui Qiu | Qiuhui Shi | Hongbin Wang | Xiang Li | Ming Gao
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Knowledge-enhanced Pre-trained Language Model (PLM) has recently received significant attention, which aims to incorporate factual knowledge into PLMs. However, most existing methods modify the internal structures of fixed types of PLMs by stacking complicated modules, and introduce redundant and irrelevant factual knowledge from knowledge bases (KBs). In this paper, to address these problems, we introduce a seminal knowledge prompting paradigm and further propose a knowledge-prompting-based PLM framework KP-PLM. This framework can be flexibly combined with existing mainstream PLMs. Specifically, we first construct a knowledge sub-graph from KBs for each context. Then we design multiple continuous prompts rules and transform the knowledge sub-graph into natural language prompts. To further leverage the factual knowledge from these prompts, we propose two novel knowledge-aware self-supervised tasks including prompt relevance inspection and masked prompt modeling. Extensive experiments on multiple natural language understanding (NLU) tasks show the superiority of KP-PLM over other state-of-the-art methods in both full-resource and low-resource settings. Our source codes will be released upon the acceptance of the paper.


pdf bib
HITSZ-HLT at SemEval-2021 Task 5: Ensemble Sequence Labeling and Span Boundary Detection for Toxic Span Detection
Qinglin Zhu | Zijie Lin | Yice Zhang | Jingyi Sun | Xiang Li | Qihui Lin | Yixue Dang | Ruifeng Xu
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

This paper presents the winning system that participated in SemEval-2021 Task 5: Toxic Spans Detection. This task aims to locate those spans that attribute to the text’s toxicity within a text, which is crucial for semi-automated moderation in online discussions. We formalize this task as the Sequence Labeling (SL) problem and the Span Boundary Detection (SBD) problem separately and employ three state-of-the-art models. Next, we integrate predictions of these models to produce a more credible and complement result. Our system achieves a char-level score of 70.83%, ranking 1/91. In addition, we also explore the lexicon-based method, which is strongly interpretable and flexible in practice.

pdf bib
融合情感分析的隐式反问句识别模型(Implicit Rhetorical Questions Recognition Model Combined with Sentiment Analysis)
Xiang Li (李翔) | Chengwei Liu (刘承伟) | Xiaoxu Zhu (朱晓旭)
Proceedings of the 20th Chinese National Conference on Computational Linguistics


pdf bib
Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
Zhiyong Wu | Lingpeng Kong | Wei Bi | Xiang Li | Ben Kao
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 neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information. Many recent studies report improvements when equipping their models with the multimodal module, despite the controversy of whether such improvements indeed come from the multimodal part. We revisit the contribution of multimodal information in MMT by devising two interpretable MMT models. To our surprise, although our models replicate similar gains as recently developed multimodal-integrated systems achieved, our models learn to ignore the multimodal information. Upon further investigation, we discover that the improvements achieved by the multimodal models over text-only counterparts are in fact results of the regularization effect. We report empirical findings that highlight the importance of MMT models’ interpretability, and discuss how our findings will benefit future research.


pdf bib
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
Qi Zhu | Zheng Zhang | Yan Fang | Xiang Li | Ryuichi Takanobu | Jinchao Li | Baolin Peng | Jianfeng Gao | Xiaoyan Zhu | Minlie Huang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. As the successor of ConvLab, ConvLab-2 inherits ConvLab’s framework but integrates more powerful dialogue models and supports more datasets. Besides, we have developed an analysis tool and an interactive tool to assist researchers in diagnosing dialogue systems. The analysis tool presents rich statistics and summarizes common mistakes from simulated dialogues, which facilitates error analysis and system improvement. The interactive tool provides an user interface that allows developers to diagnose an assembled dialogue system by interacting with the system and modifying the output of each system component.

pdf bib
Xiaomi’s Submissions for IWSLT 2020 Open Domain Translation Task
Yuhui Sun | Mengxue Guo | Xiang Li | Jianwei Cui | Bin Wang
Proceedings of the 17th International Conference on Spoken Language Translation

This paper describes the Xiaomi’s submissions to the IWSLT20 shared open domain translation task for Chinese<->Japanese language pair. We explore different model ensembling strategies based on recent Transformer variants. We also further strengthen our systems via some effective techniques, such as data filtering, data selection, tagged back translation, domain adaptation, knowledge distillation, and re-ranking. Our resulting Chinese->Japanese primary system ranked second in terms of character-level BLEU score among all submissions. Our resulting Japanese->Chinese primary system also achieved a competitive performance.

pdf bib
Modeling Discourse Structure for Document-level Neural Machine Translation
Junxuan Chen | Xiang Li | Jiarui Zhang | Chulun Zhou | Jianwei Cui | Bin Wang | Jinsong Su
Proceedings of the First Workshop on Automatic Simultaneous Translation

Recently, document-level neural machine translation (NMT) has become a hot topic in the community of machine translation. Despite its success, most of existing studies ignored the discourse structure information of the input document to be translated, which has shown effective in other tasks. In this paper, we propose to improve document-level NMT with the aid of discourse structure information. Our encoder is based on a hierarchical attention network (HAN) (Miculicich et al., 2018). Specifically, we first parse the input document to obtain its discourse structure. Then, we introduce a Transformer-based path encoder to embed the discourse structure information of each word. Finally, we combine the discourse structure information with the word embedding before it is fed into the encoder. Experimental results on the English-to-German dataset show that our model can significantly outperform both Transformer and Transformer+HAN.

pdf bib
Reading Comprehension as Natural Language Inference:A Semantic Analysis
Anshuman Mishra | Dhruvesh Patel | Aparna Vijayakumar | Xiang Li | Pavan Kapanipathi | Kartik Talamadupula
Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics

In the recent past, Natural language Inference (NLI) has gained significant attention, particularly given its promise for downstream NLP tasks. However, its true impact is limited and has not been well studied. Therefore, in this paper, we explore the utility of NLI for one of the most prominent downstream tasks, viz. Question Answering (QA). We transform one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both these forms. We propose new characterizations of questions, and evaluate the performance of QA and NLI models on these categories. We highlight clear categories for which the model is able to perform better when the data is presented in a coherent entailment form, and a structured question-answer concatenation form, respectively.

pdf bib
ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning
Michael Boratko | Xiang Li | Tim O’Gorman | Rajarshi Das | Dan Le | Andrew McCallum
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Given questions regarding some prototypical situation — such as Name something that people usually do before they leave the house for work? — a human can easily answer them via acquired experiences. There can be multiple right answers for such questions, with some more common for a situation than others. This paper introduces a new question answering dataset for training and evaluating common sense reasoning capabilities of artificial intelligence systems in such prototypical situations. The training set is gathered from an existing set of questions played in a long-running international trivia game show – Family Feud. The hidden evaluation set is created by gathering answers for each question from 100 crowd-workers. We also propose a generative evaluation task where a model has to output a ranked list of answers, ideally covering all prototypical answers for a question. After presenting multiple competitive baseline models, we find that human performance still exceeds model scores on all evaluation metrics with a meaningful gap, supporting the challenging nature of the task.


pdf bib
ConvLab: Multi-Domain End-to-End Dialog System Platform
Sungjin Lee | Qi Zhu | Ryuichi Takanobu | Zheng Zhang | Yaoqin Zhang | Xiang Li | Jinchao Li | Baolin Peng | Xiujun Li | Minlie Huang | Jianfeng Gao
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As a showcase, we extend the MultiWOZ dataset with user dialog act annotations to train all component models and demonstrate how ConvLab makes it easy and effortless to conduct complicated experiments in multi-domain end-to-end dialog settings.


pdf bib
Few-Shot Charge Prediction with Discriminative Legal Attributes
Zikun Hu | Xiang Li | Cunchao Tu | Zhiyuan Liu | Maosong Sun
Proceedings of the 27th International Conference on Computational Linguistics

Automatic charge prediction aims to predict the final charges according to the fact descriptions in criminal cases and plays a crucial role in legal assistant systems. Existing works on charge prediction perform adequately on those high-frequency charges but are not yet capable of predicting few-shot charges with limited cases. Moreover, these exist many confusing charge pairs, whose fact descriptions are fairly similar to each other. To address these issues, we introduce several discriminative attributes of charges as the internal mapping between fact descriptions and charges. These attributes provide additional information for few-shot charges, as well as effective signals for distinguishing confusing charges. More specifically, we propose an attribute-attentive charge prediction model to infer the attributes and charges simultaneously. Experimental results on real-work datasets demonstrate that our proposed model achieves significant and consistent improvements than other state-of-the-art baselines. Specifically, our model outperforms other baselines by more than 50% in the few-shot scenario. Our codes and datasets can be obtained from https://github.com/thunlp/attribute_charge.

pdf bib
Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures
Luke Vilnis | Xiang Li | Shikhar Murty | Andrew McCallum
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Embedding methods which enforce a partial order or lattice structure over the concept space, such as Order Embeddings (OE), are a natural way to model transitive relational data (e.g. entailment graphs). However, OE learns a deterministic knowledge base, limiting expressiveness of queries and the ability to use uncertainty for both prediction and learning (e.g. learning from expectations). Probabilistic extensions of OE have provided the ability to somewhat calibrate these denotational probabilities while retaining the consistency and inductive bias of ordered models, but lack the ability to model the negative correlations found in real-world knowledge. In this work we show that a broad class of models that assign probability measures to OE can never capture negative correlation, which motivates our construction of a novel box lattice and accompanying probability measure to capture anti-correlation and even disjoint concepts, while still providing the benefits of probabilistic modeling, such as the ability to perform rich joint and conditional queries over arbitrary sets of concepts, and both learning from and predicting calibrated uncertainty. We show improvements over previous approaches in modeling the Flickr and WordNet entailment graphs, and investigate the power of the model.

pdf bib
Sound Signal Processing with Seq2Tree Network
Weicheng Ma | Kai Cao | Zhaoheng Ni | Peter Chin | Xiang Li
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)


pdf bib
Commonsense Knowledge Base Completion
Xiang Li | Aynaz Taheri | Lifu Tu | Kevin Gimpel
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
Improving Event Detection with Abstract Meaning Representation
Xiang Li | Thien Huu Nguyen | Kai Cao | Ralph Grishman
Proceedings of the First Workshop on Computing News Storylines

pdf bib
Improving Event Detection with Active Learning
Kai Cao | Xiang Li | Miao Fan | Ralph Grishman
Proceedings of the International Conference Recent Advances in Natural Language Processing

pdf bib
Improving Event Detection with Dependency Regularization
Kai Cao | Xiang Li | Ralph Grishman
Proceedings of the International Conference Recent Advances in Natural Language Processing

pdf bib
Tackling Sparsity, the Achilles Heel of Social Networks: Language Model Smoothing via Social Regularization
Rui Yan | Xiang Li | Mengwen Liu | Xiaohua Hu
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)


pdf bib
Confidence Estimation for Knowledge Base Population
Xiang Li | Ralph Grishman
Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP 2013

pdf bib
Towards Fine-grained Citation Function Classification
Xiang Li | Yifan He | Adam Meyers | Ralph Grishman
Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP 2013

pdf bib
Iterative Transformation of Annotation Guidelines for Constituency Parsing
Xiang Li | Wenbin Jiang | Yajuan Lü | Qun Liu
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)


pdf bib
Cross-lingual Slot Filling from Comparable Corpora
Matthew Snover | Xiang Li | Wen-Pin Lin | Zheng Chen | Suzanne Tamang | Mingmin Ge | Adam Lee | Qi Li | Hao Li | Sam Anzaroot | Heng Ji
Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web


pdf bib
Annotating Event Chains for Carbon Sequestration Literature
Heng Ji | Xiang Li | Angelo Lucia | Jianting Zhang
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

In this paper we present a project of annotating event chains for an important scientific domain ― carbon sequestration. This domain aims to reduce carbon emissions and has been identified by the U.S. National Academy of Engineering (NAE) as a grand challenge problem for the 21st century. Given a collection of scientific literature, we identify a set of centroid experiments; and then link and order the observations and events centered around these experiments on temporal or causal chains. We describe the fundamental challenges on annotations and our general solutions to address them. We expect that our annotation efforts will produce significant advances in inter-operability through new information extraction techniques and permit scientists to build knowledge that will provide better understanding of important scientific challenges in this domain, share and re-use of diverse data sets and experimental results in a more efficient manner. In addition, the annotations of metadata and ontology for these literature will provide important support for data lifecycle activities.

pdf bib
Domain-Independent Novel Event Discovery and Semi-Automatic Event Annotation
Hao Li | Xiang Li | Heng Ji | Yuval Marton
Proceedings of the 24th Pacific Asia Conference on Language, Information and Computation