期刊文献+

汉语语义选择限制知识的自动获取研究 被引量:5

Research on Chinese Selectional Preferences Acquisition
下载PDF
导出
摘要 语义选择限制刻画了谓语对论元的语义选择倾向,是一种重要的词汇语义知识,对自然语言的句法、语义分析具有重要作用。该文研究汉语语义选择限制知识的自动获取,提出基于HowNet和基于LDA(Latent Dirichlet Allocation)的两种知识获取方法,对方法进行了实验对比与分析。实验表明,前者所获取的知识可理解性更好,后者所获取的知识应用效果更好。两种方法具有很好的互补性,我们提出了一个二者的融合方案。 Selectional preference describes the semantic preference of the predicate for its arguments. It is an important lexical knowledge which can be applied to syntactic and semantic analysis of natural languages. This paper studies the automatic acquisition of Chinese selectional preferences and proposes a HowNet based method and a LDA (Latent Dirichlet Allocation) based method. A comparative study shows that the former method acquires better understood knowledge while the latter achieves better performance in application. The two methods are complementary and may'oe combineal in process.
出处 《中文信息学报》 CSCD 北大核心 2014年第5期66-73,共8页 Journal of Chinese Information Processing
基金 国家博士后科学基金(2011M501184) 河南省博士后科研资助(2010027) 计算语言学教育部重点实验室(北京大学)开放课题(201301) 国家自然科学基金(60970083 61170163 61272221 61402419) 国家社会科学基金(14BYY096) 国家863计划项目(2012AA011101) 河南省科技厅科技攻关计划项目(132102210407)
关键词 语义选择限制 知识获取 HOWNET LDA(Latent DIRICHLET Allocation) selectional preference knowledge acquisition HowNet LDA (Latent Dirichlet Allocation)
  • 相关文献

参考文献19

  • 1Y Wilks.A Preferential Pattern-seeking Semantics for Natural Language Inference[J].Artificial Intelligence,1975,6:53-74.
  • 2Guangyou Zhou,Jun Zhao,Kang Liu,et al.Exploiting Web-Derived Selectional Preference to Improve Statistical Dependency Parsing[C]//Proceedings of ACL2011,2011:1556-1565.
  • 3邵艳秋,穗志方,吴云芳.基于词汇语义特征的中文语义角色标注研究[J].中文信息学报,2009,23(6):3-10. 被引量:7
  • 4P Resnik.Selection and Information:A Classed Based Approach to Lexical Relationships[D].University of Pennsylvania,Philadelphia,PA,1993.
  • 5Shane Bergsma,Dekang Lin,Randy Goebel.Discriminative Learning of Selectional Preference from Unlabeled Text[C]//Proceedings of EMNLP2008,2008,59-68.
  • 6Yuxiang Jia,Shiwen Yu.Unsupervised Chinese Verb Metaphor Recognition Based on Selectional Preferences[C]//Proceedings of the 22nd Pacific Asia Conference on Language,Information and Computation(PACLIC 22),2008:207-214.
  • 7吴云芳,段慧明,俞士汶.动词对宾语的语义选择限制[J].语言文字应用,2005(2):121-128. 被引量:18
  • 8贾玉祥,俞士汶.语义选择限制的自动获取及其在隐喻处理中的应用[C]//第四届全国学生计算语言学研讨会(SWCL 2008),2008:90-96.
  • 9董振东.HowNet[DB/OL].[2008-01-07].http://www.keenage.com/html/e_index.html.
  • 10柏晓鹏.现代汉语词义分类体系的建立和自动标注[D].新加坡国立大学博士学位论文,2012.

二级参考文献33

  • 1陈耀东,王挺,陈火旺.浅层语义分析研究[J].计算机研究与发展,2008,45(z1):321-325. 被引量:12
  • 2刘怀军,车万翔,刘挺.中文语义角色标注的特征工程[J].中文信息学报,2007,21(1):79-84. 被引量:39
  • 3袁毓林.语义角色的精细等级及其在信息处理中的应用[J].中文信息学报,2007,21(4):10-20. 被引量:45
  • 4Fillmore, Charles J. and Collin F. Baker. FrameNet Frame Semantics Meets the Corpus [D]. Poster presentation, 74th Annual Meeting of the Linguistics Society of America, 2000.
  • 5Palmer, M. , Gildea, D. , Kingsbury, P. The Proposition Bank : A Corpus Annotated with Semantic Roles[J]. Computational Linguistics, 2005,31 (1) : 71-105.
  • 6R. S. Swier, S. Stevenson. Unsupervised Semantic Role Labelling, [C]//Proceedings of EMNLP 2004: 95-102.
  • 7R. D. Nielsen, S. Pradhan. Mixing Weak Learners in Semantic Parsing[C]//Proceedings of EMNLP-2004, Barcelona, Spain, 2004: 80-87.
  • 8S. Pradhan, K. Hacioglu, V. Krugler, et al. Support Vector Learning for Semantic Argument Classification [J]. Machine Learning Journal. 2005, 60(3) : 11-39.
  • 9T. Liu, W. Che, S. Li, et al. Semantic Role Labeling System Using Maximum Entropy Classifier[C]//Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), Ann Arbor, Michigan: Association for Computational Linguistics, 2005: 189-192.
  • 10T. Cohn and P. Blunsom. Semantic Role Labelling with Tree Conditional Random Fields [C]//Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), 2005 : 169-172.

共引文献24

同被引文献26

引证文献5

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部