基于图式的文本蕴涵识别初探

倪盛俭,姬东鸿

PDF(709 KB)
PDF(709 KB)
中文信息学报 ›› 2015, Vol. 29 ›› Issue (3) : 82-87.
语编标注与推理

基于图式的文本蕴涵识别初探

  • 倪盛俭1,姬东鸿2
作者信息 +

A Tentative Study on Schemata Based Textual Entailment Recognition

  • NI Shengjian1, JI Donghong2
Author information +
History +

摘要

文本蕴涵识别是大部分自然语言信息处理应用的核心。该文尝试探讨文本蕴涵识别中涉及的(意象)图式理据。通过对选自语料例子的分析,显示各类图式是如何成为文本蕴涵识别的理据的。图式包括物性结构、理想认知模型、框架、脚本等。这些图式都是表示语义信息的结构。从广义上讲它们都可以纳入语义特征的范畴,都可能成为蕴涵关系成立的理据。基于图式的文本蕴涵识别研究结合有关图式库的构建,有望为突破文本蕴涵识别瓶颈作出重要贡献。

Abstract

Recognition of Textual Entailment (RTE) is of substantial significance to most natural language processing. This paper explores the schematic explanations to TE, revealing how (image) schemata can justify the TE results by case studies. Schemata include qualia structure, idealized cognitive model, and frame, script, etc., all of which are structures that can be used for representing word meaning. In a broad sense, all these kinds of schemata belong to the category of semantic feature and thus have the potential to become evidences for TE. Exploration into RTE based on schemata and the construction of corresponding corpora of schemata may contribute to solving the bottleneck issues in RTE.

关键词

文本蕴涵识别 / 图式 / 物性结构 / 理想认知模型 / 框架 / 脚本

Key words

RTE / schema / qualia structure (QS) / idealized cognitive model (ICM) / frame / script

引用本文

导出引用
倪盛俭,姬东鸿. 基于图式的文本蕴涵识别初探. 中文信息学报. 2015, 29(3): 82-87
NI Shengjian, JI Donghong. A Tentative Study on Schemata Based Textual Entailment Recognition. Journal of Chinese Information Processing. 2015, 29(3): 82-87

参考文献

[1] Pazienza Pennacchiotti, M Zanzotto. A linguistic inspection of textual entailment. Advances in Artificial Intelligence[C]//Proceedings in Lecture Notes in Artificial Intelligence, 2005, (3673): 315-326.
[2] 冯志伟. 计算语言学的历史回顾与现状分析[J]. 外国语,2011(1): 9-17.
[3] Ungerer F, Schmid H J. An Introduction to Cognitive Linguistics[M]. Beijing: Foreign Language Teaching and Research Press, 2001: F27.
[4] Pustejovsky J. The Generative Lexicon[J]. Massachusetts: Massachusetts Institute of Technology, 1996: 60-140.
[5] 宋作艳. 生成词库理论的最新发展[J]. 语言学论丛,2001,43(6): 202-221.
[6] Pustejovsky J. Type Theory and Lexical Decomposition[J]. Journal of Cognitive Science, 2006,(6): 39-76.
[7] Lakoff G. Women, Fire, and Dangerous Things: What Categories Reveal about the Mind[M]. Chicago and London: The University of Chicago Press, 1987: 68-71, 74, 106, 133-134, 154, 159-376, 487.
[8] 王寅. 语义理论与语言教学[M]. 上海: 上海外语教育出版社,2001: 192.
[9] 王寅. 认知语言学探索[M]. 重庆: 重庆出版社, 2005: 140.
[10] Schank R C, Abelson R P. Scripts, Plans, and Knowledge[M].Yale University, New Haven, Connecticut, 1975:152.
[11] Fillmore Charles J. Frame Semantics in Linguistics[C]//Proceedings of In the Morning Calm. Seoul: Hanshin Publishing Co., 1982: 111-137.
[12] FrameNet [OL],http://www.icsi.berkeley.edu/~framenet/, accessed 10/20/2011.
[13] Langacker R W. Cognitive Grammar: A Basic Introduction[M]. New York: Oxford University Press, 2008: 73-76.
[14] Abelson R P. Psychological status of the script concept[J]. American Psychologisl, 1981, 36: 715-729.
[15] 计道宏. 预设的语用功能研究[J]. 东北师大学报(哲学社会科学版),2011,(5): 101-103.
[16] Lakoff G, Johnson M. Metaphors we live by[M]. London: The university of Chicago press, 2003: 246, 253.
[17] Burchardt A, et al. Assessing the impact of frame semantics on textual entailment[J]. Nat. Lang. Engineering, 2009, 15(4): 527-550.
[18] Ion A, Prodromos M. A Survey of Paraphrasing and Textual Entailment Methods[J]. Journal of Artificial Intelligence Research, 2010, 38: 135-187.
[19] 张鹏,等. 基于FrameNet框架关系的文本蕴含识别[J]. 中文信息学报,2012,26(2): 46-50.
[20] Murray W R. Conceptual Metaphor and Scripts in Recognizing Textual Entailment. Natural Language Processing and Cognitive Science[C]//Proceedings, 2008:127-136.
[21] 冯志伟. 自然语言处理中的一些宏观问题之我见[J]. 中国外语,2009,(5): 36-41.
[22] 束定芳. 认知语义学的基本原理 、研究目标与方法[J]. 山东外语教学,2005,(5): 3-11.

基金

安徽省2014年质量工程教学研究重点项目(2014JYXM236);国家自然科学基金(61173062,61202193)。
PDF(709 KB)

559

Accesses

0

Citation

Detail

段落导航
相关文章

/