Peifeng Li


2021

pdf bib
Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation
Feng Jiang | Yaxin Fan | Xiaomin Chu | Peifeng Li | Qiaoming Zhu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Implicit discourse relation recognition (IDRR) is a critical task in discourse analysis. Previous studies only regard it as a classification task and lack an in-depth understanding of the semantics of different relations. Therefore, we first view IDRR as a generation task and further propose a method joint modeling of the classification and generation. Specifically, we propose a joint model, CG-T5, to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. Furthermore, we design three target sentence forms, including the question form, for the generation model to incorporate prior knowledge. To address the issue that large discourse units are hardly embedded into the target sentence, we also propose a target sentence construction mechanism that automatically extracts core sentences from those large discourse units. Experimental results both on Chinese MCDTB and English PDTB datasets show that our model CG-T5 achieves the best performance against several state-of-the-art systems.

2020

pdf bib
融合全局和局部信息的汉语宏观篇章结构识别(Combining Global and Local Information to Recognize Chinese Macro Discourse Structure)
Yaxin Fan (范亚鑫) | Feng Jiang (蒋峰) | Xiaomin Chu (褚晓敏) | Peifeng Li (李培峰) | Qiaoming Zhu (朱巧明)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

作为宏观篇章分析中的基础任务,篇章结构识别任务的目的是识别相邻篇章单元之间的结构,并层次化构建篇章结构树。已有的工作只考虑局部的结构和语义信息或只考虑全局信息。因此,本文提出了一种融合全局和局部信息的指针网络模型,该模型在考虑全局的语义信息同时,又考虑局部段落间的语义关系密切程度,从而有效地提高宏观篇章结构识别的能力。在汉语宏观篇章树库(MCDTB)的实验结果表明,本文所提出的模型性能优于目前性能最好的模型。

pdf bib
基于阅读理解框架的中文事件论元抽取(Chinese Event Argument Extraction using Reading Comprehension Framework)
Min Chen (陈敏) | Fan Wu (吴凡) | Zhongqing Wang (王中卿) | Peifeng Li (李培峰) | Qiaoming Zhu (朱巧明)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

传统的事件论元抽取方法把该任务当作句子中实体提及的多分类或序列标注任务,论元角色的类别在这些方法中只能作为向量表示,而忽略了论元角色的先验信息。实际上,论元角色的语义和论元本身有很大关系。对此,本文提议将其当作机器阅读理解任务,把论元角色表述为自然语言描述的问题,通过在上下文中回答这些问题来抽取论元。该方法更好地利用了论元角色类别的先验信息,在ACE2005中文语料上的实验证明了该方法的有效性。

pdf bib
基于半监督学习的中文社交文本事件聚类方法(Semi-supervised Method to Cluster Chinese Events on Social Streams)
Hengrui Guo (郭恒睿) | Zhongqing Wang (王中卿) | Peifeng Li (李培峰) | Qiaoming Zhu (朱巧明)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

面向社交媒体的事件聚类旨在根据事件特征对短文本聚类。目前,事件聚类模型主要分为无监督模型和有监督模型。无监督模型聚类效果较差,有监督模型依赖大量标注数据。基于此,本文提出了一种半监督事件聚类模型(SemiEC),该模型在小规模标注数据的基础上,利用LSTM表征事件,利用线性模型计算文本相似度,进行增量聚类,利用增量聚类产生的标注数据对模型再训练,结束后对不确定样本再聚类。实验表明,SemiEC的性能相比其他模型均有所提高。

pdf bib
Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading
Feng Jiang | Xiaomin Chu | Peifeng Li | Fang Kong | Qiaoming Zhu
Proceedings of the 28th International Conference on Computational Linguistics

Discourse structure tree construction is the fundamental task of discourse parsing and most previous work focused on English. Due to the cultural and linguistic differences, existing successful methods on English discourse parsing cannot be transformed into Chinese directly, especially in paragraph level suffering from longer discourse units and fewer explicit connectives. To alleviate the above issues, we propose two reading modes, i.e., the global backward reading and the local reverse reading, to construct Chinese paragraph level discourse trees. The former processes discourse units from the end to the beginning in a document to utilize the left-branching bias of discourse structure in Chinese, while the latter reverses the position of paragraphs in a discourse unit to enhance the differentiation of coherence between adjacent discourse units. The experimental results on Chinese MCDTB demonstrate that our model outperforms all strong baselines.

pdf bib
A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure
Longyin Zhang | Yuqing Xing | Fang Kong | Peifeng Li | Guodong Zhou
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Due to its great importance in deep natural language understanding and various down-stream applications, text-level parsing of discourse rhetorical structure (DRS) has been drawing more and more attention in recent years. However, all the previous studies on text-level discourse parsing adopt bottom-up approaches, which much limit the DRS determination on local information and fail to well benefit from global information of the overall discourse. In this paper, we justify from both computational and perceptive points-of-view that the top-down architecture is more suitable for text-level DRS parsing. On the basis, we propose a top-down neural architecture toward text-level DRS parsing. In particular, we cast discourse parsing as a recursive split point ranking task, where a split point is classified to different levels according to its rank and the elementary discourse units (EDUs) associated with it are arranged accordingly. In this way, we can determine the complete DRS as a hierarchical tree structure via an encoder-decoder with an internal stack. Experimentation on both the English RST-DT corpus and the Chinese CDTB corpus shows the great effectiveness of our proposed top-down approach towards text-level DRS parsing.

2019

pdf bib
Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese
Sheng Xu | Peifeng Li | Fang Kong | Qiaoming Zhu | Guodong Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

In the literature, most of the previous studies on English implicit discourse relation recognition only use sentence-level representations, which cannot provide enough semantic information in Chinese due to its unique paratactic characteristics. In this paper, we propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations. In particular, besides encoding arguments (discourse units) using a gated convolutional network to obtain sentence-level representations, we train a simplified topic model to infer the latent topic-level representations. Moreover, we feed the two pairs of representations to two factored tensor networks, respectively, to capture both the sentence-level interactions and topic-level relevance using multi-slice tensors. Experimentation on CDTB, a Chinese discourse corpus, shows that our proposed model significantly outperforms several state-of-the-art baselines in both micro and macro F1-scores.

pdf bib
Document-Level Event Factuality Identification via Adversarial Neural Network
Zhong Qian | Peifeng Li | Qiaoming Zhu | Guodong Zhou
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)

Document-level event factuality identification is an important subtask in event factuality and is crucial for discourse understanding in Natural Language Processing (NLP). Previous studies mainly suffer from the scarcity of suitable corpus and effective methods. To solve these two issues, we first construct a corpus annotated with both document- and sentence-level event factuality information on both English and Chinese texts. Then we present an LSTM neural network based on adversarial training with both intra- and inter-sequence attentions to identify document-level event factuality. Experimental results show that our neural network model can outperform various baselines on the constructed corpus.

2018

pdf bib
Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse
Sheng Xu | Peifeng Li | Guodong Zhou | Qiaoming Zhu
Proceedings of the 27th International Conference on Computational Linguistics

The task of nuclearity recognition in Chinese discourse remains challenging due to the demand for more deep semantic information. In this paper, we propose a novel text matching network (TMN) that encodes the discourse units and the paragraphs by combining Bi-LSTM and CNN to capture both global dependency information and local n-gram information. Moreover, it introduces three components of text matching, the Cosine, Bilinear and Single Layer Network, to incorporate various similarities and interactions among the discourse units. Experimental results on the Chinese Discourse TreeBank show that our proposed TMN model significantly outperforms various strong baselines in both micro-F1 and macro-F1.

pdf bib
MCDTB: A Macro-level Chinese Discourse TreeBank
Feng Jiang | Sheng Xu | Xiaomin Chu | Peifeng Li | Qiaoming Zhu | Guodong Zhou
Proceedings of the 27th International Conference on Computational Linguistics

In view of the differences between the annotations of micro and macro discourse rela-tionships, this paper describes the relevant experiments on the construction of the Macro Chinese Discourse Treebank (MCDTB), a higher-level Chinese discourse corpus. Fol-lowing RST (Rhetorical Structure Theory), we annotate the macro discourse information, including discourse structure, nuclearity and relationship, and the additional discourse information, including topic sentences, lead and abstract, to make the macro discourse annotation more objective and accurate. Finally, we annotated 720 articles with a Kappa value greater than 0.6. Preliminary experiments on this corpus verify the computability of MCDTB.

2016

pdf bib
Global Inference to Chinese Temporal Relation Extraction
Peifeng Li | Qiaoming Zhu | Guodong Zhou | Hongling Wang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Previous studies on temporal relation extraction focus on mining sentence-level information or enforcing coherence on different temporal relation types among various event mentions in the same sentence or neighboring sentences, largely ignoring those discourse-level temporal relations in nonadjacent sentences. In this paper, we propose a discourse-level global inference model to mine those temporal relations between event mentions in document-level, especially in nonadjacent sentences. Moreover, we provide various kinds of discourse-level constraints, which derived from event semantics, to further improve our global inference model. Evaluation on a Chinese corpus justifies the effectiveness of our discourse-level global inference model over two strong baselines.

pdf bib
Speculation and Negation Scope Detection via Convolutional Neural Networks
Zhong Qian | Peifeng Li | Qiaoming Zhu | Guodong Zhou | Zhunchen Luo | Wei Luo
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
Employing Event Inference to Improve Semi-Supervised Chinese Event Extraction
Peifeng Li | Qiaoming Zhu | Guodong Zhou
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf bib
Argument Inference from Relevant Event Mentions in Chinese Argument Extraction
Peifeng Li | Qiaoming Zhu | Guodong Zhou
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Joint Modeling of News Reader’s and Comment Writer’s Emotions
Huanhuan Liu | Shoushan Li | Guodong Zhou | Chu-Ren Huang | Peifeng Li
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2012

pdf bib
Employing Compositional Semantics and Discourse Consistency in Chinese Event Extraction
Peifeng Li | Guodong Zhou | Qiaoming Zhu | Libin Hou
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

pdf bib
Employing Morphological Structures and Sememes for Chinese Event Extraction
Peifeng Li | Guodong Zhou
Proceedings of COLING 2012

pdf bib
Joint Modeling of Trigger Identification and Event Type Determination in Chinese Event Extraction
Peifeng Li | Qiaoming Zhu | Hongjun Diao | Guodong Zhou
Proceedings of COLING 2012

2011

pdf bib
Using Context Inference to Improve Sentence Ordering for Multi-document Summarization
Peifeng Li | Guangxi Deng | Qiaoming Zhu
Proceedings of 5th International Joint Conference on Natural Language Processing