在计算机科学和语言学中,针对动词语义层面上的分类问题,研究者们提出了不同的分类方法,但这些分类方法无一例外地都存在着分类不全面等分类学中经常遇到的问题。一个动词表示一个事件,该文以获取事件相关的常识知识为出发点,以动词性语素为分类依据对常见的现代汉语动词进行语义分类,此分类方法分类标准清晰、不丢失语义信息,并且可实现自动分类,该文重点以“自移”类动词为例来介绍我们的分类方法。此外,该文用描述逻辑对动词性语素及语素之间的分类关系进行形式化表示,动词性语素的形式化表示是动词形式化表示的基础。根据该事件语义分类结构,可以有效地进行事件属性常识知识和事件关系常识知识的获取。
Abstract
Since a verb denotes an event, we classify common modern Chinese verbs at a semantic level based on verb morphemes for the purpose of acquiring commonsense knowledge of events. In contrast to the existing linguistic verb classification taxonomy, the categorization criteria of this method is clear: preserving the semantic information contained in this verb after a verb is classified. This paper utilizes the class of "self-motion events" as an example to introduce our categorization method. We use description logics to formalize the verb morphemes and relationships between these verb morphemes, which is essential to formalization of verbs. According to this event classification system, we can effectively acquire commonsense knowledge related to event attributes and event relationships.
关键词
事件语义分类 /
特征属性 /
常识知识获取
{{custom_keyword}} /
Key words
semantic categorization of events /
characteristic attribute /
commonsense knowledge acquisition
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] COHEN H. Handbook of categorization in cognitive science[J]. British Journal of General Practice the Journal of the Royal College of General Practitioners, 2005, 40(333): 150-153.
[2] 詹卫东, 刘群. 词的语义分类在汉英机器翻译中所起的作用以及难以处理的问题[C]. 全国计算机语言学联合学术会议, 1997.
[3] LI J H, WANG R B, WANG W L, et al. Automatic labeling of semantic roles on Chinese FrameNet[J]. Journal of Software, 2010, 21(21): 597-611.
[4] PARK S B, YOO E, KIM H, et al. Automatic emotion annotation of movie dialogue using WordNet[M]. Intelligent Information and Database Systems, 2011.
[5] GAN K W, WANG C Y, MAK B. Knowledge-based sense pruning using the HowNet: An alternative to word sense disambiguation[C]//Proceedings of the International Symposium on Chinese Spoken Language Processing, 2002.
[6] BAI R, WANG X, LIAO J. Extract semantic information from WordNet to improve text classification performance[M]. Advances in Computer Science and Information Technology, 2010: 409-420.
[7] FELLBAUM C, MILLER G. WordNet: An electronic lexical database[M]. MIT Press, 1998.
[8] DONG Z, QIANG D. HowNet: A hybrid language and knowledge resource[C]//Proceedings of the International Conference on Natural Language Processing & Knowledge Engineering, 2003.
[9] 马洪海. 汉语框架语义研究[M]. 北京: 中国社会科学出版社, 2010.
[10] 刘海琴. 现代汉语位移动词研究[D]. 上海: 复旦大学硕士学位论文, 2011.
[11] 冯璐璐. 现代汉语认知心理动词句研究[D]. 南京: 南京师范大学硕士学位论文,2015.
[12] 吴剑锋. 言语行为与汉语句类研究[M]. 上海: 上海交通大学出版社, 2015.
[13] LEVIN B. English verb classes and alternations: A preliminary investigation[M]. University of Chicago press, 1993.
[14] LOWE J B. The Berkeley FrameNet project[J]. Proceedings of the COLING-ACL,1998, 47(4): 86-90.
[15] KIPPER K, DANG H T, PALMER M. Class-based construction of a verb lexicon[C]//Proceedings of the 17th National Conference on Artificial Intelligence & Twelfth Conference on Innovative Applications of Artificial Intelligence, 2000: 691-696.
[16] 鲁川. 知识工程语言学[M]. 北京: 清华大学出版社, 2010.
[17] 符淮青. 词义和构成词的语素义的关系[J]. 辞书研究, 1981(01): 102-114.
[18] 中国社会科学院语言研究所词典室. 现代汉语词典[M]. 6版. 北京: 商务印书馆, 2012.
[19] 刘扬, 林子, 康司辰. 汉语的语素概念提取与语义构词分析[J]. 中文信息学报, 2018, 032(002): 12-21.
[20] ROTHSTEIN S. Structuring events: A study in the semantics of lexical aspect[M]. John Wiley & Sons, 2008.
[21] Shoham Y. Why knowledge representation matters[J]. Communications of the Acm, 2015, 59(1): 47-49.
[22] BAADER F, et al. The description logic handbook: Theory, implementation and applications[M]. Cambridge University Press, 2003.
[23] ZHOU H, YOUNG T, HUANG M, et al. Commonsense knowledge aware conversation generation with graph attention[C]//Proceedings of the IJCAI, 2018: 4623-4629.
[24] CHEN J, CHEN J, YU Z. Incorporating structured commonsense knowledge in story completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33: 6244-6251.
[25] KUMAR S K, DIVVALA S, FARHADI A, et al. Dock: Detecting objects by transferring common-sense knowledge[C]//Proceedings of the European Conference on Computer Vision, 2018: 492-508.
[26] ZELLERS R, BISK Y, FARHADI A, et al. From recognition to cognition: Visual commonsense reasoning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 6720-6731.
[27] FELLBAUM C. English Verbs as a semantic net[J]. International Journal of Lexicography, 1990, 3(4): 278-301.
[28] 袁毓林, 卢达威. 怎样利用语言知识资源进行语义理解和常识推理[J]. 中文信息学报, 2018, 32(12): 11-23.
[29] Li ZH-Y, DING X, Liu T. Constructing narrative event evolutionary graph for script event prediction[C]//Proceedings of the International Joint Conference on Artificial Intelligence, 2018: 4201-4207
[31] DING X, LI Z, LIU T, et al. ELG: An event logic graph[J]. arXiv: 1907.08015, 2019.
[31] 王亚,曹存根. 基于事件属性的事件分类研究[J]. 中文信息学报, 2020, 34(10): 39-50.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点研究与发展计划(2017YFC1700300,2017YFB1002300);国家自然科学基金(61702234)
{{custom_fund}}
PDF(3216 KB)
