期刊文献+

基于HowNet的图模型词义消歧方法 被引量:3

Word Sense Disambiguation Method Based on HowNet and Graph Model
下载PDF
导出
摘要 作为自然语言处理的一项基础性研究,词义消歧对机器翻译、信息检索、文本分类、情感分析等上层应用有重要影响。本文针对现有消歧方法中存在的对知网知识利用不充分问题,提出了一种基于How Net的图模型词义消歧方法。该方法利用依存句法分析获取上下文知识,构建上下文消歧图,并对How Net中有着重要词义区分能力的例句进行依存句法分析,构建依存消歧图,结合上下文消歧图和依存消歧图完成歧义词的消歧处理。实验结果表明,该方法在Sem Eval-2007 task#5数据集上取得了0.468的消歧准确率,获得优于同类方法的消歧效果。 As a basic research of natural language processing,word sense disambiguation(WSD)has important influence on high-level applications,such as machine translation,information retrieval,text classification and sentiment analysis.Aiming at solving the problem of the insufficient utilization of HowNet knowledge in the existing disambiguation methods,this paper proposes a WSD method based on HowNet and graph model.This method uses the techniques of dependency parsing to acquire contextual knowledge,and to construct the dependency disambiguation graph.With the help of dependency parsing,this method processes the examples in HowNet with good ability of sense distinction,to construct the dependency disambiguation graph.Then,it completes the process of disambiguation by combining dependency disambiguation graph and contextual disambiguation graph.Experimental results show that this method achieves disambiguation accuracy of 0.468 on the dataset of SemEval-2007 task#5,which is better than results given by other similar methods.
作者 孟凡擎 鹿文鹏 张旭 成金勇 MENG Fan-qing;LU Wen-peng;ZHANG Xu;CHENG Jin-yong(School of Computer Science and Technology,Qilu University of Technology(Shandong Academy of Sciences),Jinan 250353,China;School of Information Science and Engineering,Zaozhuang University,Zaozhuang 277160,China)
出处 《齐鲁工业大学学报》 2018年第6期66-73,共8页 Journal of Qilu University of Technology
基金 国家自然科学基金(61502259) 山东省自然科学基金(ZR2017MF056)
关键词 词义消歧 图模型 HOWNET 依存句法分析 word sense disambiguation graph model HowNet dependency parsing
  • 相关文献

参考文献3

二级参考文献27

  • 1陈文亮,朱靖波,朱慕华,姚天顺.基于领域词典的文本特征表示[J].计算机研究与发展,2005,42(12):2155-2160. 被引量:22
  • 2卢志茂,刘挺,李生.统计词义消歧的研究进展[J].电子学报,2006,34(2):333-343. 被引量:28
  • 3卢志茂,刘挺,李生.基于无指导机器学习的全文词义自动标注方法[J].自动化学报,2006,32(2):228-236. 被引量:2
  • 4Navigli R. Word sense disambiguation: a survey. ACM Com- puting Surveys, 2009, 41(2): 1011-1069. 被引量:1
  • 5Agirre E, de Lacalle O L, Soroa A. Knowledge-based WSD and specific domains: performing better than generic super- vised WSD. In: Proceedings of the 2009 International Joint Conference on Artificial Intelligence 2009. Pasadena, USA: Morgan Kaufmann Publishers Inc, 2009. 1501-1506. 被引量:1
  • 6Magnini B, Strapparava C, Pezzulo G, Gliozzo A. The role of domain information in word sense disambiguation. Natu- ral Language Engineering, 2002, 8(4): 359-373. 被引量:1
  • 7Navigli R, Ponzetto S P. BabelNet: the automatic construc- tion, evaluation and application of a wide-coverage multi- lingual semantic network. Artitcial Intelligence, 2012, 193: 217-250. 被引量:1
  • 8Stevenson M, Agirre E, Soroa A. Exploiting domain in- formation for word sense disambiguation of medical doc- uments. Journal of the American Medical Informatics Asso- ciation, 2011, 19(2): 235-240. 被引量:1
  • 9Agirre E, de Lacalle O L, Fellbaum C, Hsieh S K, Tesconi M, Monachini M, Vossen P, Seqers R. SemEval-2010 task 17: all-words word sense disambiguation on a specific do- main. In: Proceedings of the 2009 NAACL HLT Workshop on Semantic Evaluations: Recent Achievements and Fhlture Directions. Boulder, Colorado: Association for Computa- tional Linguistics, 2009. 123-128. 被引量:1
  • 10Agirre E, Soroa A. Personalizing PageRank for word sense disambiguation. In: Proceedings of the 12th Conference of the European Chapter of the ACL. Stroudsburg: Associa- tion for Computational Linguistics, 2009. 33-41. 被引量:1

共引文献28

同被引文献7

引证文献3

二级引证文献4

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