篇章关系分析是一种专门针对篇章语义关系及修辞结构进行分析与处理的自然语言理解任务。隐式篇章关系分析是其中重要的研究子任务,要求在显式关联线索缺失的情况下,自动检测特定论元对之间的语义关系类别。目前,隐式篇章关系分析性能较低,主流检测方法的准确率仅约为40%。造成这一现状的主要原因是: 现有方法脱离论元的语义框架进行关系分析与检测,仅仅局限于特定论元特征的关联分析。针对这一问题,该文提出一种基于框架语义的隐式篇章关系推理方法,这一方法有效利用了框架语义知识库(即FrameNet)和相关识别技术,实现了论元语义框架的自动识别,并在此基础上,借助大规模文本数据中框架语义关联关系的分布概率,进行论元语义一级的关系判定。实验结果显示,仅仅利用第一层框架语义知识,即可提高隐式篇章关系检测性能至少5.14%;同时,在考虑关系类别平衡性的情况下,这一方法能提高至少10.68%。
Abstract
Discourse relation analysis is a task of natural language understanding which aimed at analyzing and disposing the semantic relation and rhetorical structure of discourse. Implicit discourse relation analysis is an important subtask of automatically detectind senses of semantic relation between arguments in the absence of direct cues. Currently, the performance of implicit discourse relation analysis is low and state-of-art accuracy can only reach 40%. The major cause of this situation is that the existing methods did not analyze arguments in the semantic frame, limited only to the local features and correlation analysis of arguments. This paper proposes a method of implicit discourse relation inference based on frame semantic. This method automatic recognised semantic frame of arguments through FrameNet and related identification technology. On this basis, we indentify the semantic relation of arguments by the distribution probability of frame semantic relation in large-scale text data. The experimental results show that, only using the first level of frame semantic can improve the detection performance of implicit discourse relation up to 5.14%; meanwhile, this method can make the accuracy rate increased by 10.68% in the case of considering the balance of relation categories.
关键词
篇章关系 /
隐式篇章关系 /
框架语义
{{custom_keyword}} /
Key words
discourse relation /
implicit discourse relation /
frame semantics
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Prasad R, Dinesh N, Lee A, et al. The Penn Discourse Treebank 2.0[C]//Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, 2008: 2961-2968.
[2] Miltsakaki E, Robaldo L, Lee A, et al. Sense annotation in the Penn Discourse Treebank. Journal of Computational Linguistics and Intelligent Text Processing, Lecture Notes in Computer Science, 2008, 4919: 275-286.
[3] Riaz M, Girju R. Another look at causality: Discovering Scenario-specific Contingency Relationships with no Supervision[C]//Proceedings of the 4th IEEE International Conference on Semantic Computing (ICSC), Pittsburgh, USA, 2010: 361-368.
[4] Do QX, Chan YS, Roth D. Minimally supervised event causality identification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Edinburgh,UK,2011: 294-303.
[5] Zhou L, Li B, Gao W, et al. Unsupervised discovery of discourse relations for eliminating intra-sentence polarity ambiguities[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Edinburgh, Scotland, UK 2011: 162-171.
[6] 王继成,武港山,周源远等. 一种篇章结构指导的中文Web文档自动摘要方法[J]. 计算机研究与发展, 2003, 40(3): 398-405.
[7] Pitler E, Raghupathy M, Mehta H, et al. Easily identifiable discourse relations[C]//Proceedings of the 22nd International Conference on Computational Linguistics (COLING), Manchester, UK, 2008: 87-90.
[8] Wang Wen-Ting, Su Jian, Tan CL. Kernel based discourse relation recognition with temporal ordering information[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), Uppsala, Sweden, 2010: 710-719.
[9] Zhou Zhi-Min, Xu Yu, Niu Zheng-Yu, et al. Predicting discourse connectives for implicit discourse relation recognition[C]//Proceedings of the 23th International Conference on Computational Linguistics (COLING), Poster, Beijing, China, 2010: 1507-1514.
[10] Napoles C, Gormley M, Durme BV. Annotated Gigaword[C]//Proceedings of the Joint Workshop on Automatic Knowledge Base Construction & Web-scale Knowledge Extraction (AKBC-WEKEX) of NAACL-HLT, Montreal, Canada, 2012: 95-100.
[11] Lin ZH, Kan MY, Ng HT. Recognizing implicit discourse relations in the Penn Discourse Treebank[C]//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, 2009: 343-351.
[12] Soricut R, Marcu D. Sentence level discourse parsing using syntactic and lexical information[C]//Proceedings of the 2003 Conference of the North America Chapter of the Association for Computational Linguistics on Human Language Technology (NAACL), Edmonton, Canada, 2003: 149-156.
[13] Marcu D, Echihabi A. An unsupervised approach to recognizing discourse relations[C]//Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Morristown, NJ, USA, 2002: 368-375.
[14] Saito M, Yamamoto K, Sekine S. Using phrasal patterns to identify discourse relations[C]//Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), New York, USA, 2006: 133-136.
[15] Fillmore CJ. Frame semantics and the nature of language[J]. Annals of the New York Academy of Sciences, 1976: 20-32.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61373097,1003152,61272259,60970056,60970057,90920004);教育部博士学科点专项基金(2009321110006,20103201110021);江苏省自然科学基金(BK2011282);江苏省高校自然科学基金重大项目(11KJA520003)以及苏州市自然科学基金(SYG201030、SH201212)
{{custom_fund}}
PDF(2636 KB)
