采用Seq2Seq模型的非受限词义消歧方法
|
摘要
词义消歧在中文自然语言处理中有着重要作用,基于传统机器学习的方法存在准确度不高,需要人工提取文本特征的缺点;基于深度学习的方法不适于词义歧义较多的情况。该文提出采用Seq2Seq模型的非受限词义消歧方法,输入词上下文序列,经过编码器编码得到潜在语义向量,再经过解码器解码输出词义序列,适用于所有词义歧义情况。最后,在SemEval-2007 Task#5任务中进行测试,测试结果表明,该文提出的方法比其他7种方法中的最优方法消歧准确率提高了11.48%。
Word sense disambiguation plays an important role in Chinese natural language processing. Existing methods based on traditional machine learning have the disadvantages of low accuracy and need to extract text features manually. Existing methods based on deep learning are not suitable for situations where the meaning of words is ambiguous. An unrestricted word sense disambiguation method using Seq2 Seq model is proposed. The input is a word context sequence. The potential semantic vector is obtained by encoder coding. The latent semantic vector is decoded by the decoder to output a sequence of word meanings. The method is applicable to all word meaning ambiguity cases. Finally, the test is carried out in the SemEval-2007 Task #5 task. The test results show that the proposed method has improved the disambiguation accuracy by 11.48% compared with the other seven methods.
Word sense disambiguation plays an important role in Chinese natural language processing. Existing methods based on traditional machine learning have the disadvantages of low accuracy and need to extract text features manually. Existing methods based on deep learning are not suitable for situations where the meaning of words is ambiguous. An unrestricted word sense disambiguation method using Seq2 Seq model is proposed. The input is a word context sequence. The potential semantic vector is obtained by encoder coding. The latent semantic vector is decoded by the decoder to output a sequence of word meanings. The method is applicable to all word meaning ambiguity cases. Finally, the test is carried out in the SemEval-2007 Task #5 task. The test results show that the proposed method has improved the disambiguation accuracy by 11.48% compared with the other seven methods.
引文
[1] 秦春秀,祝婷,赵捧未,等.自然语言语义分析研究进展[J].图书情报工作,2014,58(22):130-137.
[2] BROWN P F,PIETRA V J D,PIETRA S A D,et al.The mathematics of statistical machine translation:Parameter estimation[J].Computational Linguistics,1993,19(2):263-311.
[3] DOLAN W B,BROCKETT C.Automatically constructing a corpus of sentential paraphrases[C]//Proceedings of the 3rd International Workshop on Paraphrasing (IWP2005),2005.
[4] ZENG D,LIU K,LAI S,et al.Relation classification via convolutional deep neural network[C]//Proceedings of COLING 2014,the 25th International Conference on Computational Linguistics:Technical Papers.Dublin,2014:2335-2344.
[5] LI H,XU J.Semantic matching in search[J].Foundations and Trends in Information Retrieval,2014,7(5):343-469.
[6] 杨安,李素建,李芸.基于领域知识和词向量的词义消歧方法[J].北京大学学报(自然科学版),2017,53(2):204-210.
[7] NAVIGLI R,LAPATA M.Graph connectivity measures for unsupervised word sense disambiguation[C]//International Joint Conference on Artificial Intelligence(IJCAI).DBLP,2007:1683-1688.
[8] 王瑞琴,孔繁胜.无监督词义消歧研究[J].软件学报,2009,20(8):2138-2152.
[9] YUAN D,DOHERTY R,RICHARDSON J,et al.Word sense disambiguation with neural language models[J].arXiv Preprint,2016:1603.
[10] CHEN X,LIU Z,SUN M.A unified model for word sense representation and disambiguation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).Association for Computational Linguistics,2014:1025-1035.
[11] 薛涛,王雅玲,穆楠.基于词义消歧的卷积神经网络文本分类模型[J].计算机应用研究,2018,35(10):2898-2903.
[12] SHEN Y,HE X,GAO J,et al.A latent semantic model with convolutional-pooling structure for information retrieval[C]//Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management.ACM,2014:101-110.
[13] MELAMUD O,GOLDBERGER J,DAGAN I.Context2vec:Learning generic context embedding with bidirectional LSTM[C]//Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning.Association for Computational Linguistics,2016:51-61.
[14] 杨陟卓.基于上下文翻译的有监督词义消歧研究[J].计算机科学,2017,44(4):252-255.
[15] 张春祥,徐志峰,高雪瑶.一种半监督的汉语词义消歧方法[J].西南交通大学学报,2019,54(2):408-414.
[16] 张国清.两种词义消歧方法分析与比较[J].信息与电脑 (理论版),2017(19):47-48.
[17] 孟禹光.基于语义相关度计算的词义消歧[D].沈阳:沈阳航空航天大学,2018.
[18] 郭鸿奇,李国佳.一种基于词语多原型向量表示的句子相似度计算方法[J].智能计算机与应用,2018,8(2):38-42.
[19] 全昌勤.基于语料库的汉语词义消歧方法研究[D].武汉:华中师范大学,2005.
[20] JIN P,WU Y,YU S.Semeval-2007 task 05:Multilingual chinese-english lexical sample[C]//Proceedings of the 4th International Workshop on Semantic Evaluations.Association for Computational Linguistics,2007:19-23.
[2] BROWN P F,PIETRA V J D,PIETRA S A D,et al.The mathematics of statistical machine translation:Parameter estimation[J].Computational Linguistics,1993,19(2):263-311.
[3] DOLAN W B,BROCKETT C.Automatically constructing a corpus of sentential paraphrases[C]//Proceedings of the 3rd International Workshop on Paraphrasing (IWP2005),2005.
[4] ZENG D,LIU K,LAI S,et al.Relation classification via convolutional deep neural network[C]//Proceedings of COLING 2014,the 25th International Conference on Computational Linguistics:Technical Papers.Dublin,2014:2335-2344.
[5] LI H,XU J.Semantic matching in search[J].Foundations and Trends in Information Retrieval,2014,7(5):343-469.
[6] 杨安,李素建,李芸.基于领域知识和词向量的词义消歧方法[J].北京大学学报(自然科学版),2017,53(2):204-210.
[7] NAVIGLI R,LAPATA M.Graph connectivity measures for unsupervised word sense disambiguation[C]//International Joint Conference on Artificial Intelligence(IJCAI).DBLP,2007:1683-1688.
[8] 王瑞琴,孔繁胜.无监督词义消歧研究[J].软件学报,2009,20(8):2138-2152.
[9] YUAN D,DOHERTY R,RICHARDSON J,et al.Word sense disambiguation with neural language models[J].arXiv Preprint,2016:1603.
[10] CHEN X,LIU Z,SUN M.A unified model for word sense representation and disambiguation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).Association for Computational Linguistics,2014:1025-1035.
[11] 薛涛,王雅玲,穆楠.基于词义消歧的卷积神经网络文本分类模型[J].计算机应用研究,2018,35(10):2898-2903.
[12] SHEN Y,HE X,GAO J,et al.A latent semantic model with convolutional-pooling structure for information retrieval[C]//Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management.ACM,2014:101-110.
[13] MELAMUD O,GOLDBERGER J,DAGAN I.Context2vec:Learning generic context embedding with bidirectional LSTM[C]//Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning.Association for Computational Linguistics,2016:51-61.
[14] 杨陟卓.基于上下文翻译的有监督词义消歧研究[J].计算机科学,2017,44(4):252-255.
[15] 张春祥,徐志峰,高雪瑶.一种半监督的汉语词义消歧方法[J].西南交通大学学报,2019,54(2):408-414.
[16] 张国清.两种词义消歧方法分析与比较[J].信息与电脑 (理论版),2017(19):47-48.
[17] 孟禹光.基于语义相关度计算的词义消歧[D].沈阳:沈阳航空航天大学,2018.
[18] 郭鸿奇,李国佳.一种基于词语多原型向量表示的句子相似度计算方法[J].智能计算机与应用,2018,8(2):38-42.
[19] 全昌勤.基于语料库的汉语词义消歧方法研究[D].武汉:华中师范大学,2005.
[20] JIN P,WU Y,YU S.Semeval-2007 task 05:Multilingual chinese-english lexical sample[C]//Proceedings of the 4th International Workshop on Semantic Evaluations.Association for Computational Linguistics,2007:19-23.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |