期刊文献+

基于CNN与双向LSTM的中文文本蕴含识别方法 被引量:23

CNN and BiLSTM Based Chinese Textual Entailment Recognition
下载PDF
导出
摘要 为了避免基于传统机器学习的中文文本蕴含识别方法需要人工筛选大量特征以及使用多种自然语言处理工具造成的错误累计问题,该文提出了基于CNN与双向LSTM的中文文本蕴含识别方法。该方法使用CNN与双向LSTM分别对句子进行编码,自动提取相关特征,然后使用全连接层进行分类得到初步的识别结果,最后使用语义规则对网络识别结果进行修正,得到最终的蕴含识别结果。在2014年RITE-VAL评测任务的数据集上MacroF1结果为61.74%,超过评测第一名的结果61.51%。实验结果表明,该方法对于中文文本蕴含识别是有效的。 A CNN and BiLSTM based Chinese textual entailment recognition method is presented.By using CNN and BiLSTM,the method can automatically extract relevant features,and then generate the initial result by a fully connected layer.The final result is further processed by semantic rules.Evaluated on the dataset of RITE-VAL in2014,the method obtains 61.74%,outperforming the top-ranked 61.51%in that evaluation campaign.
作者 谭咏梅 刘姝雯 吕学强 TAN Yongmei;LIU Shuwen;LV Xueqiang(School of Computer Science,Beijing University of Posts and Telecommunications,Beijing 100876,China;Beijing Key Laboratory of Internet Culture and Digital Dissemination Research,Beijing Information Science and Technology University,Beijing 100101,China)
出处 《中文信息学报》 CSCD 北大核心 2018年第7期11-19,共9页 Journal of Chinese Information Processing
基金 网络文化与数字传播北京市重点实验室开放课题(ICDD201703) 国家自然科学基金(61671070)
关键词 中文文本蕴含 卷积神经网络 双向长短时记忆网络 Chinese textual entailment convolutional neural network bidirectional long short-term memory network
  • 相关文献

参考文献2

二级参考文献19

  • 1董振东,董强,郝长伶.知网的理论发现[J].中文信息学报,2007,21(4):3-9. 被引量:99
  • 2Hideki Shima,Hiroshi Kanayama,Cheng-Wei Lee,et al.Overview of NTCIR-9 RITE:Recognizing Inference in TExt[C]//Proceedings of National Institute of Informatics.The 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:291-301.
  • 3Yaoyun Zhang,Jun Xu,Chenlong Liu,et al.ICRC_HITSZ at RITE:Leveraging Multiple Classifiers Voting for Textual Entailment Recognition[C]//Proceedings of National Institute of Informatics.The 9th NT-CIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:325-329.
  • 4Ling Cao,Xipeng Qiu,Xuanjing Huang.FudanNLP at RITE 2011:a Shallo w Semantic Approach to Textual Entailment[C]//Proceedings of National Institute of Informatics.The 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:335-338.
  • 5Hen-Hsen Huang,Kai-Chun Chang,Hayer II J.M.C.et al.NTU Textual Entailment System for NTCIR 9 RITE Task[C]//Proceedings of National Institute of Informatics.The 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:349-352.
  • 6Ranxu Su,Sheng Shang,Pan Wang,et al.ZSWSL Text Entailment Recognizing System at NTCIR-9 RITE Task[C]//Proceedings of National Institute of Informatics.The 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:394-399.
  • 7Han Ren,Chen Lv,Donghong Ji.The WHUTE System in NTCIR-9 RITE Task[C]//Proceedings of National Institute of Informatics.The 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:373-378.
  • 8Shih-Hung Wu,Wan-Chi Huang,Liang-Pu Chen,et al.Binary-class and Multi-class Chinese Textual Entailment System Description in NTCIR-9 RITE[C]//Proceedings of National Institute of Informatics.The 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:422-426.
  • 9Maofu Liu,Yan Li,Donghong Ji,et al.Atomic Event Semantic Roles and Chinese Instances Analysis[C]//Proceedings of Donghong Ji & Guozheng Xiao (Eds.).Chinese Lexical Semantics.Berlin,Heidelberg:Springer-Verlag,2013:110-121.
  • 10Maofu Liu,Yan Li,Yu Xiao,et al.WUST SVM-Based System at NTCIR-9 RITE Task[C]//Proceedings of National Institute of Informatics.The 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies:Information Retrieval,Question Answering and Cross-Lingual Information Access.Tokyo,Japan:National Institute of Informatics,2011:318-324.

共引文献35

同被引文献154

引证文献23

二级引证文献121

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