Peng Li


2023

pdf bib
Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks
Zhicheng Guo | Sijie Cheng | Yile Wang | Peng Li | Yang Liu
Findings of the Association for Computational Linguistics: ACL 2023

Retrieval-augmented methods have received increasing attention to support downstream tasks by leveraging useful information from external resources. Recent studies mainly focus on exploring retrieval to solve knowledge-intensive (KI) tasks. However, the potential of retrieval for most non-knowledge-intensive (NKI) tasks remains under-explored. There are two main challenges to leveraging retrieval-augmented methods for NKI tasks: 1) the demand for diverse relevance score functions and 2) the dilemma between training cost and task performance. To address these challenges, we propose a two-stage framework for NKI tasks, named PGRA. In the first stage, we adopt a task-agnostic retriever to build a shared static index and select candidate evidence efficiently. In the second stage, we design a prompt-guided reranker to rerank the nearest evidence according to task-specific relevance for the reader. Experimental results show that PGRA outperforms other state-of-the-art retrieval-augmented methods. Our analyses further investigate the influence factors to model performance and demonstrate the generality of PGRA. The code and model will be released for further research.

pdf bib
Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions
Ziyue Wang | Chi Chen | Peng Li | Yang Liu
Findings of the Association for Computational Linguistics: EMNLP 2023

Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question answering (OK-VQA). As images are invisible to LLMs, researchers convert images to text to engage LLMs into the visual question reasoning procedure. This leads to discrepancies between images and their textual representations presented to LLMs, which consequently impedes final reasoning performance. To fill the information gap and better leverage the reasoning capability, we design a framework that enables LLMs to proactively ask relevant questions to unveil more details in the image, along with filters for refining the generated information. We validate our idea on OK-VQA and A-OKVQA. Our method continuously boosts the performance of baselines methods by an average gain of 2.15% on OK-VQA, and achieves consistent improvements across different LLMs.

pdf bib
Self-Knowledge Guided Retrieval Augmentation for Large Language Models
Yile Wang | Peng Li | Maosong Sun | Yang Liu
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models (LLMs) have shown superior performance without task-specific fine-tuning. Despite the success, the knowledge stored in the parameters of LLMs could still be incomplete and difficult to update due to the computational costs. As complementary, retrieval-based methods can offer non-parametric world knowledge and improve the performance on tasks such as question answering. However, we find that the retrieved knowledge does not always help and even has a negative impact on original responses occasionally. To better make use of both internal knowledge and external world knowledge, we investigate eliciting the model’s ability to recognize what they know and do not know (which is also called “self-knowledge”) and propose Self-Knowledge guided Retrieval augmentation (SKR), a simple yet effective method which can let LLMs refer to the questions they have previously encountered and adaptively call for external resources when dealing with new questions. We evaluate SKR on multiple datasets and demonstrate that it outperforms chain-of-thought based and fully retrieval-based methods by using either InstructGPT or ChatGPT.

pdf bib
Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation
Zeyuan Yang | Peng Li | Yang Liu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Large Language Models (LLMs) have showcased impressive performance. However, due to their inability to capture relationships among samples, these frozen LLMs inevitably keep repeating similar mistakes. In this work, we propose our Tuning-free Rule Accumulation (TRAN) framework, which guides LLMs in improving their performance by learning from previous mistakes. Considering data arrives sequentially, LLMs gradually accumulate rules from incorrect cases, forming a rule collection. These rules are then utilized by the LLMs to avoid making similar mistakes when processing subsequent inputs. Moreover, the rules remain independent of the primary prompts, seamlessly complementing prompt design strategies. Experimentally, we show that TRAN improves over recent baselines by a large margin.

pdf bib
Revisiting Source Context in Nearest Neighbor Machine Translation
Xuanhong Li | Peng Li | Po Hu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Nearest neighbor machine translation (kNN-MT), which interpolates target token probabilities with estimates derived from additional examples, has achieved significant improvements and attracted extensive interest in recent years. However, existing research does not explicitly consider the source context when retrieving similar examples, potentially leading to suboptimal performance. To address this, we comprehensively revisit the role of source context and propose a simple and effective method for improving neural machine translation via source context enhancement, demonstrating its crucial role in both retrieving superior examples and determining more suitable interpolation coefficients. Furthermore, we reveal that the probability estimation can be further optimized by incorporating a source-aware distance calibration module. Comprehensive experiments show that our proposed approach can be seamlessly integrated with representative kNN-MT baselines, resulting in substantial improvements over these strong baselines across a number of settings and domains. Remarkably, these improvements can reach up to 1.6 BLEU points.

pdf bib
Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation
Kaiyu Huang | Peng Li | Junpeng Liu | Maosong Sun | Yang Liu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Although existing multilingual neural machine translation (MNMT) models have demonstrated remarkable performance to handle multiple translation directions in a single model and achieved zero-shot translation between language pairs unseen in training, they still suffer from relatively poor translation qualities for some language pairs. A practical scenario is that how to continually update MNMT models for both supervised and zero-shot translations when limited new data arrives. To this end, we propose a two-stage approach that encourages original models to acquire language-agnostic multilingual representations from new data, and preserves the model architecture without introducing parameters. Experimental results and further analysis demonstrate that our method can efficiently improve performance of existing MNMT models in translation directions where they are initially weak, and mitigates the degeneration in the original well-performing translation directions, offering flexibility in the real-world scenario.

pdf bib
Continual Knowledge Distillation for Neural Machine Translation
Yuanchi Zhang | Peng Li | Maosong Sun | Yang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

While many parallel corpora are not publicly accessible for data copyright, data privacy and competitive differentiation reasons, trained translation models are increasingly available on open platforms. In this work, we propose a method called continual knowledge distillation to take advantage of existing translation models to improve one model of interest. The basic idea is to sequentially transfer knowledge from each trained model to the distilled model. Extensive experiments on Chinese-English and German-English datasets show that our method achieves significant and consistent improvements over strong baselines under both homogeneous and heterogeneous trained model settings and is robust to malicious models.

pdf bib
Weakly Supervised Vision-and-Language Pre-training with Relative Representations
Chi Chen | Peng Li | Maosong Sun | Yang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaining decent performance on downstream tasks. However, current WVLP methods use only local descriptions of images, i.e., object tags, as cross-modal anchors to construct weakly-aligned image-text pairs for pre-training. This affects the data quality and thus the effectiveness of pre-training. In this paper, we propose to directly take a small number of aligned image-text pairs as anchors, and represent each unaligned image and text by its similarities to these anchors, i.e., relative representations. We build a WVLP framework based on the relative representations, namely RELIT, which collects high-quality weakly-aligned image-text pairs from large-scale image-only and text-only data for pre-training through relative representation-based retrieval and generation. Experiments on four downstream tasks show that RELIT achieves new state-of-the-art results under the weakly supervised setting.

pdf bib
Plug-and-Play Knowledge Injection for Pre-trained Language Models
Zhengyan Zhang | Zhiyuan Zeng | Yankai Lin | Huadong Wang | Deming Ye | Chaojun Xiao | Xu Han | Zhiyuan Liu | Peng Li | Maosong Sun | Jie Zhou
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Injecting external knowledge can improve the performance of pre-trained language models (PLMs) on various downstream NLP tasks. However, massive retraining is required to deploy new knowledge injection methods or knowledge bases for downstream tasks. In this work, we are the first to study how to improve the flexibility and efficiency of knowledge injection by reusing existing downstream models. To this end, we explore a new paradigm plug-and-play knowledge injection, where knowledge bases are injected into frozen existing downstream models by a knowledge plugin. Correspondingly, we propose a plug-and-play injection method map-tuning, which trains a mapping of knowledge embeddings to enrich model inputs with mapped embeddings while keeping model parameters frozen. Experimental results on three knowledge-driven NLP tasks show that existing injection methods are not suitable for the new paradigm, while map-tuning effectively improves the performance of downstream models. Moreover, we show that a frozen downstream model can be well adapted to different domains with different mapping networks of domain knowledge. Our code and models are available at https://github.com/THUNLP/Knowledge-Plugin.

pdf bib
Hard Sample Aware Prompt-Tuning
Yuanjian Xu | Qi An | Jiahuan Zhang | Peng Li | Zaiqing Nie
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability. To achieve the best performance for NLP tasks with just a few samples, it is vital to include as many informative samples as possible and to avoid misleading ones. However, there is no work in prompt-tuning literature addressing the problem of differentiating informative hard samples from misleading ones in model training, which is challenging due to the lack of supervision signals about the quality of the samples to train a well-performed model. We propose a Hard Sample Aware Prompt-Tuning framework (i.e. HardPT) to solve the non-differentiable problem in hard sample identification with reinforcement learning, and to strengthen the discrimination of the feature space without changing the original data distribution via an adaptive contrastive learning method. An extensive empirical study on a series of NLP tasks demonstrates the capability of HardPT in few-shot scenarios. HardPT obtains new SOTA results on all evaluated NLP tasks, including pushing the SST-5 accuracy to 49.5% (1.1% point absolute improvement), QNLI accuracy to 74.6% (1.9% absolute improvement), NMLI accuracy to 71.5 (0.7% absolute improvement), TACREV F1-score to 28.2 (1.0 absolute improvement), and i2b2/VA F1-score to 41.2 (1.3 absolute improvement).

pdf bib
Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models
Qinhong Zhou | Zonghan Yang | Peng Li | Yang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Conventional knowledge distillation (KD) methods require access to the internal information of teachers, e.g., logits. However, such information may not always be accessible for large pre-trained language models (PLMs). In this work, we focus on decision-based KD for PLMs, where only teacher decisions (i.e., top-1 labels) are accessible. Considering the information gap between logits and decisions, we propose a novel method to estimate logits from the decision distributions. Specifically, decision distributions can be both derived as a function of logits theoretically and estimated with test-time data augmentation empirically. By combining the theoretical and empirical estimations of the decision distributions together, the estimation of logits can be successfully reduced to a simple root-finding problem. Extensive experiments show that our method significantly outperforms strong baselines on both natural language understanding and machine reading comprehension datasets.

pdf bib
An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation
Xuancheng Huang | Zijun Liu | Peng Li | Tao Li | Maosong Sun | Yang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recently, multi-aspect controllable text generation that controls the generated text in multiple aspects (e.g., sentiment, topic, and keywords) has attracted increasing attention. Although methods based on parameter efficient tuning like prefix-tuning could achieve multi-aspect controlling in a plug-and-play way, the mutual interference of multiple prefixes leads to significant degeneration of constraints and limits their extensibility to training-time unseen aspect combinations. In this work, we provide a theoretical lower bound for the interference and empirically found that the interference grows with the number of layers where prefixes are inserted. Based on these analyses, we propose using trainable gates to normalize the intervention of prefixes to restrain the growing interference. As a result, controlling training-time unseen combinations of aspects can be realized by simply concatenating corresponding plugins such that new constraints can be extended at a lower cost. In addition, we propose a unified way to process both categorical and free-form constraints. Experiments on text generation and machine translation demonstrate the superiority of our approach over baselines on constraint accuracy, text quality, and extensibility.

pdf bib
Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation
Kaiyu Huang | Peng Li | Jin Ma | Ting Yao | Yang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In the real-world scenario, a longstanding goal of multilingual neural machine translation (MNMT) is that a single model can incrementally adapt to new language pairs without accessing previous training data. In this scenario, previous studies concentrate on overcoming catastrophic forgetting while lacking encouragement to learn new knowledge from incremental language pairs, especially when the incremental language is not related to the set of original languages. To better acquire new knowledge, we propose a knowledge transfer method that can efficiently adapt original MNMT models to diverse incremental language pairs. The method flexibly introduces the knowledge from an external model into original models, which encourages the models to learn new language pairs, completing the procedure of knowledge transfer. Moreover, all original parameters are frozen to ensure that translation qualities on original language pairs are not degraded. Experimental results show that our method can learn new knowledge from diverse language pairs incrementally meanwhile maintaining performance on original language pairs, outperforming various strong baselines in incremental learning for MNMT.

pdf bib
CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors
Peng Li | Tianxiang Sun | Qiong Tang | Hang Yan | Yuanbin Wu | Xuanjing Huang | Xipeng Qiu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning ability on many NLP tasks. A common practice is to recast the task into a text-to-text format such that generative LLMs of natural language (NL-LLMs) like GPT-3 can be prompted to solve it. However, it is nontrivial to perform information extraction (IE) tasks with NL-LLMs since the output of the IE task is usually structured and therefore is hard to be converted into plain text. In this paper, we propose to recast the structured output in the form of code instead of natural language and utilize generative LLMs of code (Code-LLMs) such as Codex to perform IE tasks, in particular, named entity recognition and relation extraction. In contrast to NL-LLMs, we show that Code-LLMs can be well-aligned with these IE tasks by designing code-style prompts and formulating these IE tasks as code generation tasks. Experiment results on seven benchmarks show that our method consistently outperforms fine-tuning moderate-size pre-trained models specially designed for IE tasks (e.g., UIE) and prompting NL-LLMs under few-shot settings. We further conduct a series of in-depth analyses to demonstrate the merits of leveraging Code-LLMs for IE tasks.

2022

pdf bib
MoEfication: Transformer Feed-forward Layers are Mixtures of Experts
Zhengyan Zhang | Yankai Lin | Zhiyuan Liu | Peng Li | Maosong Sun | Jie Zhou
Findings of the Association for Computational Linguistics: ACL 2022

Recent work has shown that feed-forward networks (FFNs) in pre-trained Transformers are a key component, storing various linguistic and factual knowledge. However, the computational patterns of FFNs are still unclear. In this work, we study the computational patterns of FFNs and observe that most inputs only activate a tiny ratio of neurons of FFNs. This phenomenon is similar to the sparsity of the human brain, which drives research on functional partitions of the human brain. To verify whether functional partitions also emerge in FFNs, we propose to convert a model into its MoE version with the same parameters, namely MoEfication. Specifically, MoEfication consists of two phases: (1) splitting the parameters of FFNs into multiple functional partitions as experts, and (2) building expert routers to decide which experts will be used for each input. Experimental results show that MoEfication can conditionally use 10% to 30% of FFN parameters while maintaining over 95% original performance for different models on various downstream tasks. Besides, MoEfication brings two advantages: (1) it significantly reduces the FLOPS of inference, i.e., 2x speedup with 25% of FFN parameters, and (2) it provides a fine-grained perspective to study the inner mechanism of FFNs. The source code of this paper can be obtained from https://github.com/thunlp/MoEfication.

pdf bib
ELLE: Efficient Lifelong Pre-training for Emerging Data
Yujia Qin | Jiajie Zhang | Yankai Lin | Zhiyuan Liu | Peng Li | Maosong Sun | Jie Zhou
Findings of the Association for Computational Linguistics: ACL 2022

Current pre-trained language models (PLM) are typically trained with static data, ignoring that in real-world scenarios, streaming data of various sources may continuously grow. This requires PLMs to integrate the information from all the sources in a lifelong manner. Although this goal could be achieved by exhaustive pre-training on all the existing data, such a process is known to be computationally expensive. To this end, we propose ELLE, aiming at efficient lifelong pre-training for emerging data. Specifically, ELLE consists of (1) function preserved model expansion, which flexibly expands an existing PLM’s width and depth to improve the efficiency of knowledge acquisition; and (2) pre-trained domain prompts, which disentangle the versatile knowledge learned during pre-training and stimulate the proper knowledge for downstream tasks. We experiment ELLE with streaming data from 5 domains on BERT and GPT. The results show the superiority of ELLE over various lifelong learning baselines in both pre-training efficiency and downstream performances. The codes are publicly available at https://github.com/thunlp/ELLE.

pdf bib
Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach
Xin Lv | Yankai Lin | Yixin Cao | Lei Hou | Juanzi Li | Zhiyuan Liu | Peng Li | Jie Zhou
Findings of the Association for Computational Linguistics: ACL 2022

In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models. However, these models are still quite behind the SOTA KGC models in terms of performance. In this work, we find two main reasons for the weak performance: (1) Inaccurate evaluation setting. The evaluation setting under the closed-world assumption (CWA) may underestimate the PLM-based KGC models since they introduce more external knowledge; (2) Inappropriate utilization of PLMs. Most PLM-based KGC models simply splice the labels of entities and relations as inputs, leading to incoherent sentences that do not take full advantage of the implicit knowledge in PLMs. To alleviate these problems, we highlight a more accurate evaluation setting under the open-world assumption (OWA), which manual checks the correctness of knowledge that is not in KGs. Moreover, motivated by prompt tuning, we propose a novel PLM-based KGC model named PKGC. The basic idea is to convert each triple and its support information into natural prompt sentences, which is further fed into PLMs for classification. Experiment results on two KGC datasets demonstrate OWA is more reliable for evaluating KGC, especially on the link prediction, and the effectiveness of our PKCG model on both CWA and OWA settings.

pdf bib
From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
Lei Li | Yankai Lin | Xuancheng Ren | Guangxiang Zhao | Peng Li | Jie Zhou | Xu Sun
Findings of the Association for Computational Linguistics: EMNLP 2022

Investigating better ways to reuse the released pre-trained language models (PLMs) can significantly reduce the computational cost and the potential environmental side-effects. This paper explores a novel PLM reuse paradigm, Knowledge Integration (KI). Without human annotations available, KI aims to merge the knowledge from different teacher-PLMs, each of which specializes in a different classification problem, into a versatile student model. To achieve this, we first derive the correlation between virtual golden supervision and teacher predictions. We then design a Model Uncertainty–aware Knowledge Integration (MUKI) framework to recover the golden supervision for the student. Specifically, MUKI adopts Monte-Carlo Dropout to estimate model uncertainty for the supervision integration. An instance-wise re-weighting mechanism based on the margin of uncertainty scores is further incorporated, to deal with the potential conflicting supervision from teachers. Experimental results demonstrate that MUKI achieves substantial improvements over baselines on benchmark datasets. Further analysis shows that MUKI can generalize well for merging teacher models with heterogeneous architectures, and even teachers major in cross-lingual datasets.

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
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation
Pei Ke | Hao Zhou | Yankai Lin | Peng Li | Jie Zhou | Xiaoyan Zhu | Minlie Huang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. Unsupervised metrics can only provide a task-agnostic evaluation result which correlates weakly with human judgments, whereas supervised ones may overfit task-specific data with poor generalization ability to other datasets. In this paper, we propose an unsupervised reference-free metric called CTRLEval, which evaluates controlled text generation from different aspects by formulating each aspect into multiple text infilling tasks. On top of these tasks, the metric assembles the generation probabilities from a pre-trained language model without any model training. Experimental results show that our metric has higher correlations with human judgments than other baselines, while obtaining better generalization of evaluating generated texts from different models and with different qualities.

pdf bib
Unsupervised Dependency Graph Network
Yikang Shen | Shawn Tan | Alessandro Sordoni | Peng Li | Jie Zhou | Aaron Courville
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.

pdf bib
Packed Levitated Marker for Entity and Relation Extraction
Deming Ye | Yankai Lin | Peng Li | Maosong Sun
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent entity and relation extraction works focus on investigating how to obtain a better span representation from the pre-trained encoder. However, a major limitation of existing works is that they ignore the interrelation between spans (pairs). In this work, we propose a novel span representation approach, named Packed Levitated Markers (PL-Marker), to consider the interrelation between the spans (pairs) by strategically packing the markers in the encoder. In particular, we propose a neighborhood-oriented packing strategy, which considers the neighbor spans integrally to better model the entity boundary information. Furthermore, for those more complicated span pair classification tasks, we design a subject-oriented packing strategy, which packs each subject and all its objects to model the interrelation between the same-subject span pairs. The experimental results show that, with the enhanced marker feature, our model advances baselines on six NER benchmarks, and obtains a 4.1%-4.3% strict relation F1 improvement with higher speed over previous state-of-the-art models on ACE04 and ACE05. Our code and models are publicly available at https://github.com/thunlp/PL-Marker

pdf bib
Fully Hyperbolic Neural Networks
Weize Chen | Xu Han | Yankai Lin | Hexu Zhao | Zhiyuan Liu | Peng Li | Maosong Sun | Jie Zhou
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in the hyperbolic space yet formalize most of their operations in the tangent space (a Euclidean subspace) at the origin of the hyperbolic model. This hybrid method greatly limits the modeling ability of networks. In this paper, we propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model by adapting the Lorentz transformations (including boost and rotation) to formalize essential operations of neural networks. Moreover, we also prove that linear transformation in tangent spaces used by existing hyperbolic networks is a relaxation of the Lorentz rotation and does not include the boost, implicitly limiting the capabilities of existing hyperbolic networks. The experimental results on four NLP tasks show that our method has better performance for building both shallow and deep networks. Our code will be released to facilitate follow-up research.

pdf bib
A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language Models
Deming Ye | Yankai Lin | Peng Li | Maosong Sun | Zhiyuan Liu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Pre-trained language models (PLMs) cannot well recall rich factual knowledge of entities exhibited in large-scale corpora, especially those rare entities. In this paper, we propose to build a simple but effective Pluggable Entity Lookup Table (PELT) on demand by aggregating the entity’s output representations of multiple occurrences in the corpora. PELT can be compatibly plugged as inputs to infuse supplemental entity knowledge into PLMs. Compared to previous knowledge-enhanced PLMs, PELT only requires 0.2%-5% pre-computation with capability of acquiring knowledge from out-of-domain corpora for domain adaptation scenario. The experiments on knowledge-related tasks demonstrate that our method, PELT, can flexibly and effectively transfer entity knowledge from related corpora into PLMs with different architectures. Our code and models are publicly available at https://github.com/thunlp/PELT

pdf bib
Event Detection with Dual Relational Graph Attention Networks
Jiaxin Mi | Po Hu | Peng Li
Proceedings of the 29th International Conference on Computational Linguistics

Event detection, which aims to identify instances of specific event types from pieces of text, is a fundamental task in information extraction. Most existing approaches leverage syntactic knowledge with a set of syntactic relations to enhance event detection. However, a side effect of these syntactic-based approaches is that they may confuse different syntactic relations and tend to introduce redundant or noisy information, which may lead to performance degradation. To this end, we propose a simple yet effective model named DualGAT (Dual Relational Graph Attention Networks), which exploits the complementary nature of syntactic and semantic relations to alleviate the problem. Specifically, we first construct a dual relational graph that both aggregates syntactic and semantic relations to the key nodes in the graph, so that event-relevant information can be comprehensively captured from multiple perspectives (i.e., syntactic and semantic views). We then adopt augmented relational graph attention networks to encode the graph and optimize its attention weights by introducing contextual information, which further improves the performance of event detection. Extensive experiments conducted on the standard ACE2005 benchmark dataset indicate that our method significantly outperforms the state-of-the-art methods and verifies the superiority of DualGAT over existing syntactic-based methods.

pdf bib
Knowledge Inheritance for Pre-trained Language Models
Yujia Qin | Yankai Lin | Jing Yi | Jiajie Zhang | Xu Han | Zhengyan Zhang | Yusheng Su | Zhiyuan Liu | Peng Li | Maosong Sun | Jie Zhou
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Recent explorations of large-scale pre-trained language models (PLMs) have revealed the power of PLMs with huge amounts of parameters, setting off a wave of training ever-larger PLMs. However, it requires tremendous computational resources to train a large-scale PLM, which may be practically unaffordable. In addition, existing large-scale PLMs are mainly trained from scratch individually, ignoring that many well-trained PLMs are available. To this end, we explore the question how could existing PLMs benefit training large-scale PLMs in future. Specifically, we introduce a pre-training framework named “knowledge inheritance” (KI) and explore how could knowledge distillation serve as auxiliary supervision during pre-training to efficiently learn larger PLMs. Experimental results demonstrate the superiority of KI in training efficiency. We also conduct empirical analyses to explore the effects of teacher PLMs’ pre-training settings, including model architecture, pre-training data, etc. Finally, we show that KI could be applied to domain adaptation and knowledge transfer.

pdf bib
On Transferability of Prompt Tuning for Natural Language Processing
Yusheng Su | Xiaozhi Wang | Yujia Qin | Chi-Min Chan | Yankai Lin | Huadong Wang | Kaiyue Wen | Zhiyuan Liu | Peng Li | Juanzi Li | Lei Hou | Maosong Sun | Jie Zhou
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Prompt tuning (PT) is a promising parameter-efficient method to utilize extremely large pre-trained language models (PLMs), which can achieve comparable performance to full-parameter fine-tuning by only tuning a few soft prompts. However, PT requires much more training time than fine-tuning. Intuitively, knowledge transfer can help to improve the efficiency. To explore whether we can improve PT via prompt transfer, we empirically investigate the transferability of soft prompts across different downstream tasks and PLMs in this work. We find that (1) in zero-shot setting, trained soft prompts can effectively transfer to similar tasks on the same PLM and also to other PLMs with a cross-model projector trained on similar tasks; (2) when used as initialization, trained soft prompts of similar tasks and projected prompts of other PLMs can significantly accelerate training and also improve the performance of PT. Moreover, to explore what decides prompt transferability, we investigate various transferability indicators and find that the overlapping rate of activated neurons strongly reflects the transferability, which suggests how the prompts stimulate PLMs is essential. Our findings show that prompt transfer is promising for improving PT, and further research shall focus more on prompts’ stimulation to PLMs. The source code can be obtained from https://github.com/thunlp/Prompt-Transferability.

pdf bib
MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction
Xiaozhi Wang | Yulin Chen | Ning Ding | Hao Peng | Zimu Wang | Yankai Lin | Xu Han | Lei Hou | Juanzi Li | Zhiyuan Liu | Peng Li | Jie Zhou
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

The diverse relationships among real-world events, including coreference, temporal, causal, and subevent relations, are fundamental to understanding natural languages. However, two drawbacks of existing datasets limit event relation extraction (ERE) tasks: (1) Small scale. Due to the annotation complexity, the data scale of existing datasets is limited, which cannot well train and evaluate data-hungry models. (2) Absence of unified annotation. Different types of event relations naturally interact with each other, but existing datasets only cover limited relation types at once, which prevents models from taking full advantage of relation interactions. To address these issues, we construct a unified large-scale human-annotated ERE dataset MAVEN-ERE with improved annotation schemes. It contains 103,193 event coreference chains, 1,216,217 temporal relations, 57,992 causal relations, and 15,841 subevent relations, which is larger than existing datasets of all the ERE tasks by at least an order of magnitude. Experiments show that ERE on MAVEN-ERE is quite challenging, and considering relation interactions with joint learning can improve performances. The dataset and source codes can be obtained from https://github.com/THU-KEG/MAVEN-ERE.

pdf bib
ROSE: Robust Selective Fine-tuning for Pre-trained Language Models
Lan Jiang | Hao Zhou | Yankai Lin | Peng Li | Jie Zhou | Rui Jiang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks.A large body of defense methods has been proposed. However, they are still limited due to redundant attack search spaces and the inability to defend against various types of attacks. In this work, we present a novel fine-tuning approach called RObust SEletive fine-tuning (ROSE) to address this issue.ROSE conducts selective updates when adapting pre-trained models to downstream tasks, filtering out invaluable and unrobust updates of parameters.Specifically, we propose two strategies: the first-order and second-order ROSE for selecting target robust parameters.The experimental results show that ROSE achieves significant improvements in adversarial robustness on various downstream NLP tasks, and the ensemble method even surpasses both variants above.Furthermore, ROSE can be easily incorporated into existing fine-tuning methods to improve their adversarial robustness further.The empirical analysis confirms that ROSE eliminates unrobust spurious updates during fine-tuning, leading to solutions corresponding to flatter and wider optima than the conventional method.Code is available at https://github.com/jiangllan/ROSE.

pdf bib
A Template-based Method for Constrained Neural Machine Translation
Shuo Wang | Peng Li | Zhixing Tan | Zhaopeng Tu | Maosong Sun | Yang Liu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose pre-specified constraints into the translation process of NMT models. Although many approaches have been proposed to address this issue, most existing methods can not satisfy the following three desiderata at the same time: (1) high translation quality, (2) high match accuracy, and (3) low latency. In this work, we propose a template-based method that can yield results with high translation quality and match accuracy and the inference speed of our method is comparable with unconstrained NMT models. Our basic idea is to rearrange the generation of constrained and unconstrained tokens through a template. Our method does not require any changes in the model architecture and the decoding algorithm. Experimental results show that the proposed template-based approach can outperform several representative baselines in both lexically and structurally constrained translation tasks.

pdf bib
Entropy-Based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation
Kaiyu Huang | Peng Li | Jin Ma | Yang Liu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In a practical real-world scenario, the longstanding goal is that a universal multilingual translation model can be incrementally updated when new language pairs arrive. Specifically, the initial vocabulary only covers some of the words in new languages, which hurts the translation quality for incremental learning. Although existing approaches attempt to address this issue by replacing the original vocabulary with a rebuilt vocabulary or constructing independent language-specific vocabularies, these methods can not meet the following three demands simultaneously: (1) High translation quality for original and incremental languages, (2) low cost for model training, (3) low time overhead for preprocessing. In this work, we propose an entropy-based vocabulary substitution (EVS) method that just needs to walk through new language pairs for incremental learning in a large-scale multilingual data updating while remaining the size of the vocabulary. Our method has access to learn new knowledge from updated training samples incrementally while keeping high translation quality for original language pairs, alleviating the issue of catastrophic forgetting. Results of experiments show that EVS can achieve better performance and save excess overhead for incremental learning in the multilingual machine translation task.

pdf bib
End-to-End Unsupervised Vision-and-Language Pre-training with Referring Expression Matching
Chi Chen | Peng Li | Maosong Sun | Yang Liu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Recently there has been an emerging interest in unsupervised vision-and-language pre-training (VLP) that learns multimodal representations without parallel image-caption data. These pioneering works significantly reduce the cost of VLP on data collection and achieve promising results compared to supervised VLP. However, existing unsupervised VLP methods take as input pre-extracted region-based visual features from external object detectors, which both limits flexibility and reduces computational efficiency. In this paper, we explore end-to-end unsupervised VLP with a vision encoder to directly encode images. The vision encoder is pre-trained on image-only data and jointly optimized during multimodal pre-training. To further enhance the learned cross-modal features, we propose a novel pre-training task that predicts which patches contain an object referred to in natural language from the encoded visual features. Extensive experiments on four vision-and-language tasks show that our approach outperforms previous unsupervised VLP methods and obtains new state-of-the-art results.

2021

pdf bib
WeChat Neural Machine Translation Systems for WMT21
Xianfeng Zeng | Yijin Liu | Ernan Li | Qiu Ran | Fandong Meng | Peng Li | Jinan Xu | Jie Zhou
Proceedings of the Sixth Conference on Machine Translation

This paper introduces WeChat AI’s participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German. Our systems are based on the Transformer (Vaswani et al., 2017) with several novel and effective variants. In our experiments, we employ data filtering, large-scale synthetic data generation (i.e., back-translation, knowledge distillation, forward-translation, iterative in-domain knowledge transfer), advanced finetuning approaches, and boosted Self-BLEU based model ensemble. Our constrained systems achieve 36.9, 46.9, 27.8 and 31.3 case-sensitive BLEU scores on English->Chinese, English->Japanese, Japanese->English and English->German, respectively. The BLEU scores of English->Chinese, English->Japanese and Japanese->English are the highest among all submissions, and that of English->German is the highest among all constrained submissions.

pdf bib
GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
Feilong Chen | Xiuyi Chen | Fandong Meng | Peng Li | Jie Zhou
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
Feilong Chen | Fandong Meng | Xiuyi Chen | Peng Li | Jie Zhou
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Unsupervised Knowledge Selection for Dialogue Generation
Xiuyi Chen | Feilong Chen | Fandong Meng | Peng Li | Jie Zhou
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction
Tianyu Gao | Xu Han | Yuzhuo Bai | Keyue Qiu | Zhiyu Xie | Yankai Lin | Zhiyuan Liu | Peng Li | Maosong Sun | Jie Zhou
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade
Lei Li | Yankai Lin | Deli Chen | Shuhuai Ren | Peng Li | Jie Zhou | Xu Sun
Findings of the Association for Computational Linguistics: EMNLP 2021

Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model. In this paper, we empirically analyze the working mechanism of dynamic early exiting and find that it faces a performance bottleneck under high speed-up ratios. On one hand, the PLMs’ representations in shallow layers lack high-level semantic information and thus are not sufficient for accurate predictions. On the other hand, the exiting decisions made by internal classifiers are unreliable, leading to wrongly emitted early predictions. We instead propose a new framework for accelerating the inference of PLMs, CascadeBERT, which dynamically selects proper-sized and complete models in a cascading manner, providing comprehensive representations for predictions. We further devise a difficulty-aware objective, encouraging the model to output the class probability that reflects the real difficulty of each instance for a more reliable cascading mechanism. Experimental results show that CascadeBERT can achieve an overall 15% improvement under 4x speed-up compared with existing dynamic early exiting methods on six classification tasks, yielding more calibrated and accurate predictions.

pdf bib
Dynamic Knowledge Distillation for Pre-trained Language Models
Lei Li | Yankai Lin | Shuhuai Ren | Peng Li | Jie Zhou | Xu Sun
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Knowledge distillation (KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected teacher model on the pre-defined training dataset. In this paper, we explore whether a dynamic knowledge distillation that empowers the student to adjust the learning procedure according to its competency, regarding the student performance and learning efficiency. We explore the dynamical adjustments on three aspects: teacher model adoption, data selection, and KD objective adaptation. Experimental results show that (1) proper selection of teacher model can boost the performance of student model; (2) conducting KD with 10% informative instances achieves comparable performance while greatly accelerates the training; (3) the student performance can be boosted by adjusting the supervision contribution of different alignment objective. We find dynamic knowledge distillation is promising and provide discussions on potential future directions towards more efficient KD methods.

pdf bib
CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild
Yuan Yao | Jiaju Du | Yankai Lin | Peng Li | Zhiyuan Liu | Jie Zhou | Maosong Sun
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Existing relation extraction (RE) methods typically focus on extracting relational facts between entity pairs within single sentences or documents. However, a large quantity of relational facts in knowledge bases can only be inferred across documents in practice. In this work, we present the problem of cross-document RE, making an initial step towards knowledge acquisition in the wild. To facilitate the research, we construct the first human-annotated cross-document RE dataset CodRED. Compared to existing RE datasets, CodRED presents two key challenges: Given two entities, (1) it requires finding the relevant documents that can provide clues for identifying their relations; (2) it requires reasoning over multiple documents to extract the relational facts. We conduct comprehensive experiments to show that CodRED is challenging to existing RE methods including strong BERT-based models.

pdf bib
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
Wenkai Yang | Yankai Lin | Peng Li | Jie Zhou | Xu Sun
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Backdoor attacks, which maliciously control a well-trained model’s outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an efficient online defense mechanism based on robustness-aware perturbations. Specifically, by analyzing the backdoor training process, we point out that there exists a big gap of robustness between poisoned and clean samples. Motivated by this observation, we construct a word-based robustness-aware perturbation to distinguish poisoned samples from clean samples to defend against the backdoor attacks on natural language processing (NLP) models. Moreover, we give a theoretical analysis about the feasibility of our robustness-aware perturbation-based defense method. Experimental results on sentiment analysis and toxic detection tasks show that our method achieves better defending performance and much lower computational costs than existing online defense methods. Our code is available at https://github.com/lancopku/RAP.

pdf bib
Context Tracking Network: Graph-based Context Modeling for Implicit Discourse Relation Recognition
Yingxue Zhang | Fandong Meng | Peng Li | Ping Jian | Jie Zhou
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Implicit discourse relation recognition (IDRR) aims to identify logical relations between two adjacent sentences in the discourse. Existing models fail to fully utilize the contextual information which plays an important role in interpreting each local sentence. In this paper, we thus propose a novel graph-based Context Tracking Network (CT-Net) to model the discourse context for IDRR. The CT-Net firstly converts the discourse into the paragraph association graph (PAG), where each sentence tracks their closely related context from the intricate discourse through different types of edges. Then, the CT-Net extracts contextual representation from the PAG through a specially designed cross-grained updating mechanism, which can effectively integrate both sentence-level and token-level contextual semantics. Experiments on PDTB 2.0 show that the CT-Net gains better performance than models that roughly model the context.

pdf bib
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning
Yujia Qin | Yankai Lin | Ryuichi Takanobu | Zhiyuan Liu | Peng Li | Heng Ji | Minlie Huang | Maosong Sun | Jie 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-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks. However, conventional pre-training objectives do not explicitly model relational facts in text, which are crucial for textual understanding. To address this issue, we propose a novel contrastive learning framework ERICA to obtain a deep understanding of the entities and their relations in text. Specifically, we define two novel pre-training tasks to better understand entities and relations: (1) the entity discrimination task to distinguish which tail entity can be inferred by the given head entity and relation; (2) the relation discrimination task to distinguish whether two relations are close or not semantically, which involves complex relational reasoning. Experimental results demonstrate that ERICA can improve typical PLMs (BERT and RoBERTa) on several language understanding tasks, including relation extraction, entity typing and question answering, especially under low-resource settings.

pdf bib
Rethinking Stealthiness of Backdoor Attack against NLP Models
Wenkai Yang | Yankai Lin | Peng Li | Jie Zhou | Xu Sun
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)

Recent researches have shown that large natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack. Backdoor attacked models can achieve good performance on clean test sets but perform badly on those input sentences injected with designed trigger words. In this work, we point out a potential problem of current backdoor attacking research: its evaluation ignores the stealthiness of backdoor attacks, and most of existing backdoor attacking methods are not stealthy either to system deployers or to system users. To address this issue, we first propose two additional stealthiness-based metrics to make the backdoor attacking evaluation more credible. We further propose a novel word-based backdoor attacking method based on negative data augmentation and modifying word embeddings, making an important step towards achieving stealthy backdoor attacking. Experiments on sentiment analysis and toxic detection tasks show that our method is much stealthier while maintaining pretty good attacking performance. Our code is available at https://github.com/lancopku/SOS.

pdf bib
CLEVE: Contrastive Pre-training for Event Extraction
Ziqi Wang | Xiaozhi Wang | Xu Han | Yankai Lin | Lei Hou | Zhiyuan Liu | Peng Li | Juanzi Li | Jie 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)

Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event characteristics, resulting in the developed EE models cannot take full advantage of large-scale unsupervised data. To this end, we propose CLEVE, a contrastive pre-training framework for EE to better learn event knowledge from large unsupervised data and their semantic structures (e.g. AMR) obtained with automatic parsers. CLEVE contains a text encoder to learn event semantics and a graph encoder to learn event structures respectively. Specifically, the text encoder learns event semantic representations by self-supervised contrastive learning to represent the words of the same events closer than those unrelated words; the graph encoder learns event structure representations by graph contrastive pre-training on parsed event-related semantic structures. The two complementary representations then work together to improve both the conventional supervised EE and the unsupervised “liberal” EE, which requires jointly extracting events and discovering event schemata without any annotated data. Experiments on ACE 2005 and MAVEN datasets show that CLEVE achieves significant improvements, especially in the challenging unsupervised setting. The source code and pre-trained checkpoints can be obtained from https://github.com/THU-KEG/CLEVE.

2020

pdf bib
MAVEN: A Massive General Domain Event Detection Dataset
Xiaozhi Wang | Ziqi Wang | Xu Han | Wangyi Jiang | Rong Han | Zhiyuan Liu | Juanzi Li | Peng Li | Yankai Lin | Jie Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Event detection (ED), which means identifying event trigger words and classifying event types, is the first and most fundamental step for extracting event knowledge from plain text. Most existing datasets exhibit the following issues that limit further development of ED: (1) Data scarcity. Existing small-scale datasets are not sufficient for training and stably benchmarking increasingly sophisticated modern neural methods. (2) Low coverage. Limited event types of existing datasets cannot well cover general-domain events, which restricts the applications of ED models. To alleviate these problems, we present a MAssive eVENt detection dataset (MAVEN), which contains 4,480 Wikipedia documents, 118,732 event mention instances, and 168 event types. MAVEN alleviates the data scarcity problem and covers much more general event types. We reproduce the recent state-of-the-art ED models and conduct a thorough evaluation on MAVEN. The experimental results show that existing ED methods cannot achieve promising results on MAVEN as on the small datasets, which suggests that ED in the real world remains a challenging task and requires further research efforts. We also discuss further directions for general domain ED with empirical analyses. The source code and dataset can be obtained from https://github.com/THU-KEG/MAVEN-dataset.

pdf bib
Disentangle-based Continual Graph Representation Learning
Xiaoyu Kou | Yankai Lin | Shaobo Liu | Peng Li | Jie Zhou | Yan Zhang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Graph embedding (GE) methods embed nodes (and/or edges) in graph into a low-dimensional semantic space, and have shown its effectiveness in modeling multi-relational data. However, existing GE models are not practical in real-world applications since it overlooked the streaming nature of incoming data. To address this issue, we study the problem of continual graph representation learning which aims to continually train a GE model on new data to learn incessantly emerging multi-relational data while avoiding catastrophically forgetting old learned knowledge. Moreover, we propose a disentangle-based continual graph representation learning (DiCGRL) framework inspired by the human’s ability to learn procedural knowledge. The experimental results show that DiCGRL could effectively alleviate the catastrophic forgetting problem and outperform state-of-the-art continual learning models. The code and datasets are released on https://github.com/KXY-PUBLIC/DiCGRL.

pdf bib
Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation
Xiuyi Chen | Fandong Meng | Peng Li | Feilong Chen | Shuang Xu | Bo Xu | Jie Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Knowledge selection plays an important role in knowledge-grounded dialogue, which is a challenging task to generate more informative responses by leveraging external knowledge. Recently, latent variable models have been proposed to deal with the diversity of knowledge selection by using both prior and posterior distributions over knowledge and achieve promising performance. However, these models suffer from a huge gap between prior and posterior knowledge selection. Firstly, the prior selection module may not learn to select knowledge properly because of lacking the necessary posterior information. Secondly, latent variable models suffer from the exposure bias that dialogue generation is based on the knowledge selected from the posterior distribution at training but from the prior distribution at inference. Here, we deal with these issues on two aspects: (1) We enhance the prior selection module with the necessary posterior information obtained from the specially designed Posterior Information Prediction Module (PIPM); (2) We propose a Knowledge Distillation Based Training Strategy (KDBTS) to train the decoder with the knowledge selected from the prior distribution, removing the exposure bias of knowledge selection. Experimental results on two knowledge-grounded dialogue datasets show that both PIPM and KDBTS achieve performance improvement over the state-of-the-art latent variable model and their combination shows further improvement.

pdf bib
Learning from Context or Names? An Empirical Study on Neural Relation Extraction
Hao Peng | Tianyu Gao | Xu Han | Yankai Lin | Peng Li | Zhiyuan Liu | Maosong Sun | Jie Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Neural models have achieved remarkable success on relation extraction (RE) benchmarks. However, there is no clear understanding what information in text affects existing RE models to make decisions and how to further improve the performance of these models. To this end, we empirically study the effect of two main information sources in text: textual context and entity mentions (names). We find that (i) while context is the main source to support the predictions, RE models also heavily rely on the information from entity mentions, most of which is type information, and (ii) existing datasets may leak shallow heuristics via entity mentions and thus contribute to the high performance on RE benchmarks. Based on the analyses, we propose an entity-masked contrastive pre-training framework for RE to gain a deeper understanding on both textual context and type information while avoiding rote memorization of entities or use of superficial cues in mentions. We carry out extensive experiments to support our views, and show that our framework can improve the effectiveness and robustness of neural models in different RE scenarios. All the code and datasets are released at https://github.com/thunlp/RE-Context-or-Names.

pdf bib
Coreferential Reasoning Learning for Language Representation
Deming Ye | Yankai Lin | Jiaju Du | Zhenghao Liu | Peng Li | Maosong Sun | Zhiyuan Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However, most existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse. To address this issue, we present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLP tasks that require coreferential reasoning, while maintaining comparable performance to previous models on other common NLP tasks. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/CorefBERT.

pdf bib
Neural Gibbs Sampling for Joint Event Argument Extraction
Xiaozhi Wang | Shengyu Jia | Xu Han | Zhiyuan Liu | Juanzi Li | Peng Li | Jie Zhou
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

Event Argument Extraction (EAE) aims at predicting event argument roles of entities in text, which is a crucial subtask and bottleneck of event extraction. Existing EAE methods either extract each event argument roles independently or sequentially, which cannot adequately model the joint probability distribution among event arguments and their roles. In this paper, we propose a Bayesian model named Neural Gibbs Sampling (NGS) to jointly extract event arguments. Specifically, we train two neural networks to model the prior distribution and conditional distribution over event arguments respectively and then use Gibbs sampling to approximate the joint distribution with the learned distributions. For overcoming the shortcoming of the high complexity of the original Gibbs sampling algorithm, we further apply simulated annealing to efficiently estimate the joint probability distribution over event arguments and make predictions. We conduct experiments on the two widely-used benchmark datasets ACE 2005 and TAC KBP 2016. The Experimental results show that our NGS model can achieve comparable results to existing state-of-the-art EAE methods. The source code can be obtained from https://github.com/THU-KEG/NGS.

pdf bib
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
Xu Han | Tianyu Gao | Yankai Lin | Hao Peng | Yaoliang Yang | Chaojun Xiao | Zhiyuan Liu | Peng Li | Jie Zhou | Maosong Sun
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

Relational facts are an important component of human knowledge, which are hidden in vast amounts of text. In order to extract these facts from text, people have been working on relation extraction (RE) for years. From early pattern matching to current neural networks, existing RE methods have achieved significant progress. Yet with explosion of Web text and emergence of new relations, human knowledge is increasing drastically, and we thus require “more” from RE: a more powerful RE system that can robustly utilize more data, efficiently learn more relations, easily handle more complicated context, and flexibly generalize to more open domains. In this paper, we look back at existing RE methods, analyze key challenges we are facing nowadays, and show promising directions towards more powerful RE. We hope our view can advance this field and inspire more efforts in the community.

pdf bib
Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation
Qiu Ran | Yankai Lin | Peng Li | Jie Zhou
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably suffers from the multi-modality problem: the target tokens may be provided by different possible translations, often causing token repetitions or missing. To alleviate this problem, we propose a novel semi-autoregressive model RecoverSAT in this work, which generates a translation as a sequence of segments. The segments are generated simultaneously while each segment is predicted token-by-token. By dynamically determining segment length and deleting repetitive segments, RecoverSAT is capable of recovering from repetitive and missing token errors. Experimental results on three widely-used benchmark datasets show that our proposed model achieves more than 4 times speedup while maintaining comparable performance compared with the corresponding autoregressive model.

pdf bib
Continual Relation Learning via Episodic Memory Activation and Reconsolidation
Xu Han | Yi Dai | Tianyu Gao | Yankai Lin | Zhiyuan Liu | Peng Li | Maosong Sun | Jie Zhou
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Continual relation learning aims to continually train a model on new data to learn incessantly emerging novel relations while avoiding catastrophically forgetting old relations. Some pioneering work has proved that storing a handful of historical relation examples in episodic memory and replaying them in subsequent training is an effective solution for such a challenging problem. However, these memory-based methods usually suffer from overfitting the few memorized examples of old relations, which may gradually cause inevitable confusion among existing relations. Inspired by the mechanism in human long-term memory formation, we introduce episodic memory activation and reconsolidation (EMAR) to continual relation learning. Every time neural models are activated to learn both new and memorized data, EMAR utilizes relation prototypes for memory reconsolidation exercise to keep a stable understanding of old relations. The experimental results show that EMAR could get rid of catastrophically forgetting old relations and outperform the state-of-the-art continual learning models.

pdf bib
WeChat Neural Machine Translation Systems for WMT20
Fandong Meng | Jianhao Yan | Yijin Liu | Yuan Gao | Xianfeng Zeng | Qinsong Zeng | Peng Li | Ming Chen | Jie Zhou | Sifan Liu | Hao Zhou
Proceedings of the Fifth Conference on Machine Translation

We participate in the WMT 2020 shared newstranslation task on Chinese→English. Our system is based on the Transformer (Vaswaniet al., 2017a) with effective variants and the DTMT (Meng and Zhang, 2019) architecture. In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese→English system achieves 36.9 case-sensitive BLEU score, which is thehighest among all submissions.

2019

pdf bib
DocRED: A Large-Scale Document-Level Relation Extraction Dataset
Yuan Yao | Deming Ye | Peng Li | Xu Han | Yankai Lin | Zhenghao Liu | Zhiyuan Liu | Lixin Huang | Jie Zhou | Maosong Sun
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs. In order to accelerate the research on document-level RE, we introduce DocRED, a new dataset constructed from Wikipedia and Wikidata with three features: (1) DocRED annotates both named entities and relations, and is the largest human-annotated dataset for document-level RE from plain text; (2) DocRED requires reading multiple sentences in a document to extract entities and infer their relations by synthesizing all information of the document; (3) along with the human-annotated data, we also offer large-scale distantly supervised data, which enables DocRED to be adopted for both supervised and weakly supervised scenarios. In order to verify the challenges of document-level RE, we implement recent state-of-the-art methods for RE and conduct a thorough evaluation of these methods on DocRED. Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts. Based on the detailed analysis on the experiments, we discuss multiple promising directions for future research. We make DocRED and the code for our baselines publicly available at https://github.com/thunlp/DocRED.

pdf bib
Towards Fine-grained Text Sentiment Transfer
Fuli Luo | Peng Li | Pengcheng Yang | Jie Zhou | Yutong Tan | Baobao Chang | Zhifang Sui | Xu Sun
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

In this paper, we focus on the task of fine-grained text sentiment transfer (FGST). This task aims to revise an input sequence to satisfy a given sentiment intensity, while preserving the original semantic content. Different from the conventional sentiment transfer task that only reverses the sentiment polarity (positive/negative) of text, the FTST task requires more nuanced and fine-grained control of sentiment. To remedy this, we propose a novel Seq2SentiSeq model. Specifically, the numeric sentiment intensity value is incorporated into the decoder via a Gaussian kernel layer to finely control the sentiment intensity of the output. Moreover, to tackle the problem of lacking parallel data, we propose a cycle reinforcement learning algorithm to guide the model training. In this framework, the elaborately designed rewards can balance both sentiment transformation and content preservation, while not requiring any ground truth output. Experimental results show that our approach can outperform existing methods by a large margin in both automatic evaluation and human evaluation.

pdf bib
Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation
Shuming Ma | Pengcheng Yang | Tianyu Liu | Peng Li | Jie Zhou | Xu Sun
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack of large parallel data is a major practical problem for many domains. In this work, we consider the scenario of low resource table-to-text generation, where only limited parallel data is available. We propose a novel model to separate the generation into two stages: key fact prediction and surface realization. It first predicts the key facts from the tables, and then generates the text with the key facts. The training of key fact prediction needs much fewer annotated data, while surface realization can be trained with pseudo parallel corpus. We evaluate our model on a biography generation dataset. Our model can achieve 27.34 BLEU score with only 1,000 parallel data, while the baseline model only obtain the performance of 9.71 BLEU score.

pdf bib
Adversarial Training for Weakly Supervised Event Detection
Xiaozhi Wang | Xu Han | Zhiyuan Liu | Maosong Sun | Peng Li
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)

Modern weakly supervised methods for event detection (ED) avoid time-consuming human annotation and achieve promising results by learning from auto-labeled data. However, these methods typically rely on sophisticated pre-defined rules as well as existing instances in knowledge bases for automatic annotation and thus suffer from low coverage, topic bias, and data noise. To address these issues, we build a large event-related candidate set with good coverage and then apply an adversarial training mechanism to iteratively identify those informative instances from the candidate set and filter out those noisy ones. The experiments on two real-world datasets show that our candidate selection and adversarial training can cooperate together to obtain more diverse and accurate training data for ED, and significantly outperform the state-of-the-art methods in various weakly supervised scenarios. The datasets and source code can be obtained from https://github.com/thunlp/Adv-ED.

pdf bib
NumNet: Machine Reading Comprehension with Numerical Reasoning
Qiu Ran | Yankai Lin | Peng Li | Jie Zhou | Zhiyuan Liu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human’s reading comprehension, which has not been well considered in existing machine reading comprehension (MRC) systems. To address this issue, we propose a numerical MRC model named as NumNet, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage. Our system achieves an EM-score of 64.56% on the DROP dataset, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers.

pdf bib
HMEAE: Hierarchical Modular Event Argument Extraction
Xiaozhi Wang | Ziqi Wang | Xu Han | Zhiyuan Liu | Juanzi Li | Peng Li | Maosong Sun | Jie Zhou | Xiang Ren
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Existing event extraction methods classify each argument role independently, ignoring the conceptual correlations between different argument roles. In this paper, we propose a Hierarchical Modular Event Argument Extraction (HMEAE) model, to provide effective inductive bias from the concept hierarchy of event argument roles. Specifically, we design a neural module network for each basic unit of the concept hierarchy, and then hierarchically compose relevant unit modules with logical operations into a role-oriented modular network to classify a specific argument role. As many argument roles share the same high-level unit module, their correlation can be utilized to extract specific event arguments better. Experiments on real-world datasets show that HMEAE can effectively leverage useful knowledge from the concept hierarchy and significantly outperform the state-of-the-art baselines. The source code can be obtained from https://github.com/thunlp/HMEAE.

pdf bib
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
Tianyu Gao | Xu Han | Hao Zhu | Zhiyuan Liu | Peng Li | Maosong Sun | Jie 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)

We present FewRel 2.0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances? (2) Can they detect none-of-the-above (NOTA) relations? To construct FewRel 2.0, we build upon the FewRel dataset by adding a new test set in a quite different domain, and a NOTA relation choice. With the new dataset and extensive experimental analysis, we found (1) that the state-of-the-art few-shot relation classification models struggle on these two aspects, and (2) that the commonly-used techniques for domain adaptation and NOTA detection still cannot handle the two challenges well. Our research calls for more attention and further efforts to these two real-world issues. All details and resources about the dataset and baselines are released at https://github.com/thunlp/fewrel.

2018

pdf bib
Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention
Xu Han | Pengfei Yu | Zhiyuan Liu | Maosong Sun | Peng Li
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Distantly supervised relation extraction employs existing knowledge graphs to automatically collect training data. While distant supervision is effective to scale relation extraction up to large-scale corpora, it inevitably suffers from the wrong labeling problem. Many efforts have been devoted to identifying valid instances from noisy data. However, most existing methods handle each relation in isolation, regardless of rich semantic correlations located in relation hierarchies. In this paper, we aim to incorporate the hierarchical information of relations for distantly supervised relation extraction and propose a novel hierarchical attention scheme. The multiple layers of our hierarchical attention scheme provide coarse-to-fine granularity to better identify valid instances, which is especially effective for extracting those long-tail relations. The experimental results on a large-scale benchmark dataset demonstrate that our models are capable of modeling the hierarchical information of relations and significantly outperform other baselines. The source code of this paper can be obtained from https://github.com/thunlp/HNRE.

2016

pdf bib
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
Jie Zhou | Ying Cao | Xuguang Wang | Peng Li | Wei Xu
Transactions of the Association for Computational Linguistics, Volume 4

Neural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are shallow and there is still a performance gap between a single NMT model and the best conventional MT system. In this work, we introduce a new type of linear connections, named fast-forward connections, based on deep Long Short-Term Memory (LSTM) networks, and an interleaved bi-directional architecture for stacking the LSTM layers. Fast-forward connections play an essential role in propagating the gradients and building a deep topology of depth 16. On the WMT’14 English-to-French task, we achieve BLEU=37.7 with a single attention model, which outperforms the corresponding single shallow model by 6.2 BLEU points. This is the first time that a single NMT model achieves state-of-the-art performance and outperforms the best conventional model by 0.7 BLEU points. We can still achieve BLEU=36.3 even without using an attention mechanism. After special handling of unknown words and model ensembling, we obtain the best score reported to date on this task with BLEU=40.4. Our models are also validated on the more difficult WMT’14 English-to-German task.

pdf bib
UTA DLNLP at SemEval-2016 Task 1: Semantic Textual Similarity: A Unified Framework for Semantic Processing and Evaluation
Peng Li | Heng Huang
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

pdf bib
UTA DLNLP at SemEval-2016 Task 12: Deep Learning Based Natural Language Processing System for Clinical Information Identification from Clinical Notes and Pathology Reports
Peng Li | Heng Huang
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

pdf bib
Multi-Granularity Chinese Word Embedding
Rongchao Yin | Quan Wang | Peng Li | Rui Li | Bin Wang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks
Xiaotian Jiang | Quan Wang | Peng Li | Bin Wang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Distant supervision is an efficient approach that automatically generates labeled data for relation extraction (RE). Traditional distantly supervised RE systems rely heavily on handcrafted features, and hence suffer from error propagation. Recently, a neural network architecture has been proposed to automatically extract features for relation classification. However, this approach follows the traditional expressed-at-least-once assumption, and fails to make full use of information across different sentences. Moreover, it ignores the fact that there can be multiple relations holding between the same entity pair. In this paper, we propose a multi-instance multi-label convolutional neural network for distantly supervised RE. It first relaxes the expressed-at-least-once assumption, and employs cross-sentence max-pooling so as to enable information sharing across different sentences. Then it handles overlapping relations by multi-label learning with a neural network classifier. Experimental results show that our approach performs significantly and consistently better than state-of-the-art methods.

2014

pdf bib
A Neural Reordering Model for Phrase-based Translation
Peng Li | Yang Liu | Maosong Sun | Tatsuya Izuha | Dakun Zhang
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf bib
Recursive Autoencoders for ITG-Based Translation
Peng Li | Yang Liu | Maosong Sun
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

2012

pdf bib
A Beam Search Algorithm for ITG Word Alignment
Peng Li | Yang Liu | Maosong Sun
Proceedings of COLING 2012: Posters

2011

pdf bib
Generating Aspect-oriented Multi-Document Summarization with Event-aspect model
Peng Li | Yinglin Wang | Wei Gao | Jing Jiang
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

2010

pdf bib
Generating Templates of Entity Summaries with an Entity-Aspect Model and Pattern Mining
Peng Li | Jing Jiang | Yinglin Wang
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Fast-Champollion: A Fast and Robust Sentence Alignment Algorithm
Peng Li | Maosong Sun | Ping Xue
Coling 2010: Posters

pdf bib
Using Clustering to Improve Retrieval Evaluation without Relevance Judgments
Zhiwei Shi | Peng Li | Bin Wang
Coling 2010: Posters

2009

pdf bib
Clustering to Find Exemplar Terms for Keyphrase Extraction
Zhiyuan Liu | Peng Li | Yabin Zheng | Maosong Sun
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

Search
Co-authors