基于HowNet的图模型词义消歧方法
|
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.
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.
引文
[1]李涓子.汉语词义消歧方法研究[D].北京:清华大学,1999.
[2] WU D K,XIA X Y.Large-scale automatic extraction of an EnglishChinese translation lexicon[J]. Machine translation,1994,9(3-4):285-313.
[3] GALLEY M,Mc KEOWN K.Improving word sense disambiguation in lexical chaining[C]. Proceedings of the 18th international joint conference on Artificial intelligence. Morgan Kaufmann Publishers Inc.,2003:1486-1488.
[4] MIHALCEA R.Co-training and self-training for word sense disambiguation[C].Proceedings of the 8th Conference on Computational Natural Language Learning(CoNLL),2004,2004:33-40.
[5] NAVIGLI R,VELARDI P. Structural semantic interconnections:a knowledge-based approach to word sense disambiguation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(7):1075-1086.
[6] AGIRRE E,SOROA A.Personalizing pagerank for word sense disambiguation[C].Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics,2009:33-41.
[7]杨陟卓,黄河燕.基于词语距离的网络图词义消歧[J].软件学报,2012,23(4):776-785.
[8]鹿文鹏,黄河燕,吴昊.基于领域知识的图模型词义消歧方法[J].自动化学报,2014,40(12):2836-2850.
[9]董振东.HowNet[EB/OL].http://www.keenage.com,2013.
[10]刘群,李素建.基于《知网》的词汇语义相似度计算[J].中文计算语言学,2002,7(2):59-76.
[11] TESNIARE L.Elaments de Synta Xe Structural[M].Paris:Klincksieck,1959.
[12] MANNING C D,SURDEANU M,BAUER J,et al. The Stanford core NLP natural language processing toolkit[C]. Association for Computational Linguistics(ACL)System Demonstrations.Association for Computational Linguistics,2014:55-60.
[13] JIN P,WU Y F,YU S W. Sem Eval-2007 task 5:Multilingual Chinese-English lexical sample task[C]. Proceedings of the 4th International Workshop on the Evaluation of Systems for the S emantic Analysis of Text. Prague:Association for Computational Linguistics,2007.19-23.
[2] WU D K,XIA X Y.Large-scale automatic extraction of an EnglishChinese translation lexicon[J]. Machine translation,1994,9(3-4):285-313.
[3] GALLEY M,Mc KEOWN K.Improving word sense disambiguation in lexical chaining[C]. Proceedings of the 18th international joint conference on Artificial intelligence. Morgan Kaufmann Publishers Inc.,2003:1486-1488.
[4] MIHALCEA R.Co-training and self-training for word sense disambiguation[C].Proceedings of the 8th Conference on Computational Natural Language Learning(CoNLL),2004,2004:33-40.
[5] NAVIGLI R,VELARDI P. Structural semantic interconnections:a knowledge-based approach to word sense disambiguation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(7):1075-1086.
[6] AGIRRE E,SOROA A.Personalizing pagerank for word sense disambiguation[C].Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics,2009:33-41.
[7]杨陟卓,黄河燕.基于词语距离的网络图词义消歧[J].软件学报,2012,23(4):776-785.
[8]鹿文鹏,黄河燕,吴昊.基于领域知识的图模型词义消歧方法[J].自动化学报,2014,40(12):2836-2850.
[9]董振东.HowNet[EB/OL].http://www.keenage.com,2013.
[10]刘群,李素建.基于《知网》的词汇语义相似度计算[J].中文计算语言学,2002,7(2):59-76.
[11] TESNIARE L.Elaments de Synta Xe Structural[M].Paris:Klincksieck,1959.
[12] MANNING C D,SURDEANU M,BAUER J,et al. The Stanford core NLP natural language processing toolkit[C]. Association for Computational Linguistics(ACL)System Demonstrations.Association for Computational Linguistics,2014:55-60.
[13] JIN P,WU Y F,YU S W. Sem Eval-2007 task 5:Multilingual Chinese-English lexical sample task[C]. Proceedings of the 4th International Workshop on the Evaluation of Systems for the S emantic Analysis of Text. Prague:Association for Computational Linguistics,2007.19-23.