“网球问题”指怎样把racquet(网球拍)、ball(网球)和net(球网)之类具有情境联想关系的词汇概念联系起来、发现它们之间的语义和推理关系。这是一个自然语言处理和相关的语言知识资源建设的世界性难题。该文以求解“网球问题”为目标,对目前比较主流的几种语言词汇和概念知识库系统(包括WordNet、VerbNet、FrameNet、ConceptNet等)进行检讨,指出它们在解决“网球问题”上还都存在一定的局限性,着重分析它们为什么不能解决“网球问题”。进而指出基于生成词库论的名词物性结构知识描写体系可以解决“网球问题”,主张用名词的物性结构知识和相关的句法组合知识来构建一种以名词(实体)为核心的词汇概念网络,以弥补上述几种知识库系统的不足,为自然语言处理提供一种可资参考的词汇概念知识库体系。
Abstract
“Tennis Problem” tries to link racquet, ball and net that are in a situational association relationship, and find the semantic and reasoning relationship among them. This is a worldwide problem in natural language processing in the construction of related language knowledge or resources. Aiming at solving the “tennis problem”, this paper reviews several mainstream systems of linguistic lexical and conceptual knowledge base (including WordNet, VerbNet, FrameNet, ConceptNet, etc.), illustrates their limitations on solving this problem, and explains on why they cannot solve it. This paper furcher proposes that the descriptive system of knowledge based on the theory of generative lexicon, i.e., the qualia structure of nouns, can be adopted, and that the qualia structure and relevant syntactic combinations can be used to build a noun-based or entity-based lexical network. This conceptual network may make up for the inadequacy of the above-mentioned systems of knowledge base and provide a knowledge base of lexical concepts for natural language processing.
关键词
“网球问题” /
Word Net /
Verb Net /
Frame Net /
Concep tNet /
物性结构
{{custom_keyword}} /
Key words
“Tennis Problem” /
WordNet /
VerbNet /
FrameNet /
ConceptNet /
Qualia Structure
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Fellbaum Christiane (ed.) WordNet: An Electronic Lexical Database [M]. Cambridge, Massachusetts: MIT Press, 1998.
[2] Miller G A, Fellbaum Christiane. WordNet then and now [J]. Lang Resources & Evaluation, 2007, 41: 209-214.
[3] Miller G A, Beckwith Richard, Fellbaum Christiane, Gross Derek, Miller K J. Introduction to WordNet: An On-line Lexical Database [J]. International Journal of Lexicography, 1990, 3(4): 236-244.
[4] 黄居仁. 语意网与中文信息化前瞻: 知识本体与自然语言处理[C]//孙茂松、陈群秀. 自然语言理解和大规模内容计算. 北京: 清华大学出版社,2005: 1-10.
[5] 袁毓林. 语义资源建设的最新趋势和长远目标——通过影射对比、走向统一联合、实现自动推理[J]. 中文信息学报,2008,22(3): 3-15.
[6] 索绪尔. 普通语言学教程[M]. 北京: 商务印书馆,1980.
[7] Warrington E K, Shallice T. Category specific semantic impairments [J]. Brain, 1984, 107(3): 829-853.
[8] Lin E L, Murphy G L. Thematic relations in adults’ concept [J]. Journal of Experimental Psychology: General, 2001, 130(1): 3-28.
[9] Altmann G. Thematic role assignment in context [J]. Journal of Memory and Language,1999, 41 (1): 124-145.
[10] Warren T, McConnel K. Investigating effects of selectional restriction violations and plausibility violation severity on eye-movement in reading [J]. Psychonomic bulletin & review, 2007, 14: 770-775.
[11] Kipper Karin, Dang H T, Palmer Martha. Class-Based Construction of a Verb Lexicon[C]//AAAI-2000 Seventeenth National Conference on Artificial Intelligence, Austin, TX, July 30-August 3, 2000.
[12] Fillmore C J, Johnson C R, Petruck M R. Background to FrameNet[J]. International Journal of Lexicography, 2003, 16 (3): 236-250.
[13] Fillmore C J. Frame Semantics[C]//Linguistics in the Moring Calm. Seoul: Hanshin Publishing Co., 1982:111-137.
[14] Baker F Collin, Charles J Fillmore, John B. Lowe. The Berkeley FrameNet Project[C]//Proceedings of the 17th International Conference on Computational Linguistics the 36th Annual Meeting on Association for Computational Linguistics, Montreal, Canada, 1998: 86-90.
[15] Henderson Harry. Milestones in Discovery and Invention: Artificial Intelligence [M]. Shanghai: Shanghai Science & Technological Literature Publishing House, 2007.
[16] Liu H, Singh P. ConceptNet-a practical commonsense reasoning toolkit [J]. BT Technology Journal, 2004, 22(4): 211-226.
[17] 袁毓林. 信息抽取的语义知识资源研究[J]. 中文信息学报,2002,16(5): 8-14.
[18] Pustejovsky J. The Generative Lexicon [J]. Computational linguistics, 1991, 17(4): 409-441.
[19] Pustejovsky J. The Generative Lexicon [M]. Cambridge, Massachusetts: MIT Press, 1995.
[20] Pustejovsky J, Bouillon P, Isahara H, et al. Advances in Generative Lexicon Theory[M]. Dordrecht: Springer, 2013.
[21] 吴国向,袁毓林. 词汇本体语义学的实证性研究[R].第五届当代语言学国际圆桌会议,南京: 南京师范大学,2013.10.
[22] Geeraerts Dirk. Theories of Lexical Semantics [M]. New York: Oxford University Press Inc., 2010.
[23] Pustejovsky James. Coercion in a general theory of argument selection [J]. Linguistics, 2011, 49 (6): 1401-1431.
[24] Moravcsik J M. Aitia as generative factor in Aristotle’s philosophy [J]. Dialogue, 1975, 14(4): 622-638.
[25] 袁毓林. 基于生成词库论和论元结构理论的语义知识体系研究[J]. 中文信息学报,2013,27(6): 23-30.
[26] 袁毓林. 汉语名词物性结构的描写体系和运用案例[J]. 当代语言学,2014,16(1): 31-48.
[27] Loper Edward. PropBank, VerbNet & SemLink[R]. Joint Meeting of the ACL/SIGSEM Working Group on Representation of Multimodal Semantic Information and the ISO Task Domain Group on Semantic Content Representation. Tilburg, the Netherlands. 2007.
[28] Loper Edward, Szu-ting Yi, Palmer Martha. Combining Lexical Resources: Mapping between PropBank and VerbNet[C]//Proceedings of the 7th International Workshop on Computational Linguistics. Tilburg, Netherlands. 2006.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点基础研究计划(973计划)项目(2014CB340502)
{{custom_fund}}
PDF(4304 KB)
