功能连接词是一种直接表述篇章单元内部语义关系、结构特性和语境发展趋势的词特征。借助功能连接词的这一优势,该文提出一种基于功能连接词的隐式篇章关系推理方法。该方法首先挖掘词级与短语级的功能连接词,划分功能连接词的篇章关系类别;其次,为每个功能连接词构建概念模型,借以描述由功能连接词连接的论元属性,并建立论元概念与篇章关系的映射体系;最后,利用统计策略识别待测论元的概念模型,并借助“概念—关系”映射体系,实现隐式篇章语义关系推理。实验结果显示,该文基于功能连接词构建概念模型的推理方法,相较于现有的基于监督学习的分类方法,系统性能获得显著提升。
Abstract
The functional connective is a word feature that directly expresses interior semantic relations, structure characteristics and the development trend of context of discourse units. Based on the functional connective, this paper puts forward a kind of methods for predicting relations of implicit discourse. First, this method mines functional connectives at the word and phraselevel, and divides the discourse relationcategory of functional connectives. Secondly, it buildsthe concept model for each type of functional connectives to describe argument attributes connected by functional connectives,and establishes the mapping system between argument concepts and discourse relations; Finally, the predictions of the implicit discoursesemantic relationis realized by statistical strategy to recognize conceptual model of argument and with “concept-relations” mapping system. The experimental results show that, the predicting method byconstructing concept model based on functional connectives, got the significant performance improvementscompared to the existing classification method based on supervised learning.
关键词
隐式篇章关系 /
功能连接词 /
论元概念模型
{{custom_keyword}} /
Key words
implicit discourse relation /
functional connective word /
argument concept model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] M Riaz, R Girju. Another look at causality: Discovering scenario-specific contingency relationships with no supervision[C]//Proceedings of the 4th ICSC, 2010: 361-368.
[2] Q X Do, Y S Chan, D Roth. Minimally supervised event causality identification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2011: 294-303.
[3] 王继成,武港山. 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.
[4] L Zhou, B Li, W Gao, 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), 2011: 162-171.
[5] E Pitler, M Raghupathy, H Mehta, et al. Easily identifiable discourse relations[C]//Proceedings of the 22nd International Conference on the COLING, 2008: 87-90.
[6] W T Wang, J Su, C L Tan. Kernel Based Discourse Relation Recognition with Temporal Ordering Information[C]//Proceedings of the 48th Annual Meeting of the ACL, 2010: 710-719.
[7] R Prasad, N Dinesh, A Lee, et al. The Penn Discourse TreeBank 2.0[C]//Proceedings of Proceedings of the 6th International Conference on LREC 2008, Morocco.
[8] L Carlson, D Marcu, M E Okurowski. Building a discourse-tagged corpus in the framework of rhetorical structure theory[C]//Proceedings of the Second SIGDIAL2001, Denmark, 2001: 1-10.
[9] D Marcu, A Echihabi. An Unsupervised Approach to Recognizing Discourse Relations[C]//Proceedings of the 40th Annual Meeting on the ACL, 2002: 368-375.
[10] M Saito, K Yamamoto, S Sekine. Using Phrasal Patterns to Identify Discourse Relations[C]//Proceedings of the Human Language Technology Conference of the NAACL, 2006: 133-136.
[11] F Wolf, E Gibson. Representing discourse coherence: a corpus-based analysis[C]//Proceedings of the 20th International Conference on the COLING, Morristown, NJ, USA, 2005: 134-140.
[12] E Pitler, A Louis, A Nenkova. Automatic Sense Prediction for Implicit Discourse Relations in Text[C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, 2009, (2): 683-691.
[13] R Soricut, D Marcu. Sentence level discourse parsing using syntactic and lexical information[C]//Proceedings of the HLT/NAACL, 2003: 149-156.
[14] Z Lin, H T Ng, M Y Kan. Automatically Evaluating Text Coherence Using Discourse Relations[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011, (2): 997-1006.
[15] Z M Zhou, Y Xu, Z Y Niu, et al. Predicting Discourse Connectives for Implicit Discourse Relation Recognition[C]//Proceedings of the 23rd International Conference on Computational Linguistics: Posters, 2010: 1507-1514.
[16] http://www.bioinf.jku.at/software/apcluster/[DB/OL].
[17] http://nlp.stanford.edu/software/lex-parser.shtml[DB/OL].
[18] E Pitler, A Nenkova. Revisiting readability: A unified framework for predicting text quality[C]//Proceedings of the Conference on the EMNLP, 2008: 186-195.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61003152,61272259,60970056,90920004),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(11KIJ520003)以及苏州市自然科学基金(SYG201030, SH201212)
{{custom_fund}}
PDF(4065 KB)
