篇章关系研究,旨在推断同一篇章内相邻或跨度在一定范围内的文本片段之间的语义连接关系。语义连接关系对篇章内容理解和结构分析都具有重要作用,成为目前篇章分析领域的重点研究内容。该文针对三个中英文篇章关系研究领域的语料库:基...篇章关系研究,旨在推断同一篇章内相邻或跨度在一定范围内的文本片段之间的语义连接关系。语义连接关系对篇章内容理解和结构分析都具有重要作用,成为目前篇章分析领域的重点研究内容。该文针对三个中英文篇章关系研究领域的语料库:基于修辞结构理论的篇章树库(Rhetorical Structure Theory Discourse Treebank,RSTDT)、宾州篇章树库(Penn Discourse Treebank,PDTB)和哈尔滨工业大学中文篇章关系语料库(HIT Chinese Discourse Treebank,HIT-CDTB),主要介绍篇章关系分析理论的语料资源与研究背景、标注与评测体系以及国内外研究现状。此外,总结相关工作,指出目前篇章关系,尤其是隐式篇章关系研究的主要难题。展开更多
针对篇章隐式关系检测较难的问题,提出了一种基于语义场景匹配的平行推理方法。该方法利用框架语义学,将论元抽象为概念一级的语义描述(简称语义场景),实现描述形式的压缩。基于大规模静态数据,通过语义场景的匹配挖掘可比较论元辅助关...针对篇章隐式关系检测较难的问题,提出了一种基于语义场景匹配的平行推理方法。该方法利用框架语义学,将论元抽象为概念一级的语义描述(简称语义场景),实现描述形式的压缩。基于大规模静态数据,通过语义场景的匹配挖掘可比较论元辅助关系推理。该方法能够在保证检测精度的同时,提升检测效率。利用宾州篇章树库(penn discourse tree bank,PDTB)对这一检测方法进行评测,检测精度为55.26%。展开更多
Discourse relation classification is a fundamental task for discourse analysis,which is essential for understanding the structure and connection of texts.Implicit discourse relation classification aims to determine th...Discourse relation classification is a fundamental task for discourse analysis,which is essential for understanding the structure and connection of texts.Implicit discourse relation classification aims to determine the relationship between adjacent sentences and is very challenging because it lacks explicit discourse connectives as linguistic cues and sufficient annotated training data.In this paper,we propose a discriminative instance selection method to construct synthetic implicit discourse relation data from easy-to-collect explicit discourse relations.An expanded instance consists of an argument pair and its sense label.We introduce the argument pair type classification task,which aims to distinguish between implicit and explicit argument pairs and select the explicit argument pairs that are most similar to natural implicit argument pairs for data expansion.We also propose a simple label-smoothing technique to assign robust sense labels for the selected argument pairs.We evaluate our method on PDTB 2.0 and PDTB 3.0.The results show that our method can consistently improve the performance of the baseline model,and achieve competitive results with the state-of-the-art models.展开更多
Discourse parsing is an important research area in natural language processing(NLP),which aims to parse the discourse structure of coherent sentences.In this survey,we introduce several different kinds of discourse pa...Discourse parsing is an important research area in natural language processing(NLP),which aims to parse the discourse structure of coherent sentences.In this survey,we introduce several different kinds of discourse parsing tasks,mainly including RST-style discourse parsing,PDTB-style discourse parsing,and discourse parsing for multiparty dialogue.For these tasks,we introduce the classical and recent existing methods,especially neural network approaches.After that,we describe the applications of discourse parsing for other NLP tasks,such as machine reading comprehension and sentiment analysis.Finally,we discuss the future trends of the task.展开更多
文摘篇章关系研究,旨在推断同一篇章内相邻或跨度在一定范围内的文本片段之间的语义连接关系。语义连接关系对篇章内容理解和结构分析都具有重要作用,成为目前篇章分析领域的重点研究内容。该文针对三个中英文篇章关系研究领域的语料库:基于修辞结构理论的篇章树库(Rhetorical Structure Theory Discourse Treebank,RSTDT)、宾州篇章树库(Penn Discourse Treebank,PDTB)和哈尔滨工业大学中文篇章关系语料库(HIT Chinese Discourse Treebank,HIT-CDTB),主要介绍篇章关系分析理论的语料资源与研究背景、标注与评测体系以及国内外研究现状。此外,总结相关工作,指出目前篇章关系,尤其是隐式篇章关系研究的主要难题。
文摘针对篇章隐式关系检测较难的问题,提出了一种基于语义场景匹配的平行推理方法。该方法利用框架语义学,将论元抽象为概念一级的语义描述(简称语义场景),实现描述形式的压缩。基于大规模静态数据,通过语义场景的匹配挖掘可比较论元辅助关系推理。该方法能够在保证检测精度的同时,提升检测效率。利用宾州篇章树库(penn discourse tree bank,PDTB)对这一检测方法进行评测,检测精度为55.26%。
基金National Natural Science Foundation of China(Grant Nos.62376166,62306188,61876113)National Key R&D Program of China(No.2022YFC3303504).
文摘Discourse relation classification is a fundamental task for discourse analysis,which is essential for understanding the structure and connection of texts.Implicit discourse relation classification aims to determine the relationship between adjacent sentences and is very challenging because it lacks explicit discourse connectives as linguistic cues and sufficient annotated training data.In this paper,we propose a discriminative instance selection method to construct synthetic implicit discourse relation data from easy-to-collect explicit discourse relations.An expanded instance consists of an argument pair and its sense label.We introduce the argument pair type classification task,which aims to distinguish between implicit and explicit argument pairs and select the explicit argument pairs that are most similar to natural implicit argument pairs for data expansion.We also propose a simple label-smoothing technique to assign robust sense labels for the selected argument pairs.We evaluate our method on PDTB 2.0 and PDTB 3.0.The results show that our method can consistently improve the performance of the baseline model,and achieve competitive results with the state-of-the-art models.
基金The research in this article is supported by the Science and Technology Innovation 2030-“New Generation Artificial Intelligence”Major Project(2018AA0101901)the National Key Research and Development Project(2018YFB1005103)+2 种基金the National Natural Science Foundation of China(Grant Nos.61772156 and 61976073)Shenzhen Foundational Research Funding(JCYJ20200109113441941)the Foundation of Heilongjiang Province(F2018013).
文摘Discourse parsing is an important research area in natural language processing(NLP),which aims to parse the discourse structure of coherent sentences.In this survey,we introduce several different kinds of discourse parsing tasks,mainly including RST-style discourse parsing,PDTB-style discourse parsing,and discourse parsing for multiparty dialogue.For these tasks,we introduce the classical and recent existing methods,especially neural network approaches.After that,we describe the applications of discourse parsing for other NLP tasks,such as machine reading comprehension and sentiment analysis.Finally,we discuss the future trends of the task.
