期刊文献+

面向细粒度隐式篇章关系识别的远距离监督特征学习算法 预览

Feature Learning by Distant Supervision for Fine-Grained Implicit Discourse Relation Identification
在线阅读 免费下载
分享 导出
摘要 针对中文细粒度隐式篇章关系识别进行研究。考虑细粒度篇章关系的方向性特点,提出一种基于远距离监督的特征学习算法。该算法使用远距离监督的方法,自动标注显式篇章数据,然后利用词与连词之间的相对位置信息,训练各个词的词表达,将词的修辞功能以及关系的方向性编码到密集词表达中,将这样的词表达应用到细粒度隐式篇章关系分类器。实验结果表明,在细粒度隐式篇章关系识别任务中,该方法的分类准确率达到49.79%,比未考虑篇章关系方向性的方法有较大程度的提高。 Aiming at the identification of Chinese fine-grained implicit discourse relation and taking the directionality characteristic in account,the authors propose a feature learning algorithm based on the distant supervision to label explicit discourse data automatically.The relative position information between conjunction and words are applied to train the intensive word representation.Then the rhetorical function of words and the directionality of relations are encoded into the representation of intensive words,which is applied to the relation classification of fine-grained implicit discourses.From the experimental studies of the proposed approach,the classification accuracy reaches 49.79%,which are better than those approaches neglecting the directionality of discourse relations.
作者 唐裕婷 李艳斌 刘露 于中华 陈黎 TANG Yuting;LI Yanbin;LIU Lu;YU Zhonghua;CHEN Li(Department of Computer Science,Sichuan University,Chengdu 610065)
出处 《北京大学学报:自然科学版》 CAS CSCD 北大核心 2019年第1期91-97,共7页 Acta Scientiarum Naturalium Universitatis
基金 四川省科技支撑项目(2014GZ0063)资助.
关键词 细粒度 隐式篇章关系 中文 词表达 方向性 fine-grained implicit discourse relation Chinese word representation directionality
作者简介 通信作者:陈黎,E-mail:cl@scu.edu.cn
  • 相关文献

参考文献2

二级参考文献56

  • 1D Marcu. The theory and practice of discourse parsing and summarization[M]. MIT Press, 2000. 被引量:1
  • 2R Girju. Automatic detection of causal relations for questions answering [C]//Proceedings of the ACL 2003 Workshop on Muhilingual Summarisation and Question Answering, 2003: 76-83. 被引量:1
  • 3S Somasundaran, J Wiebe, J Ruppenhofer. Discourse- level opinion interpretation[C]//Proceedings of Coling 2008. 被引量:1
  • 4Zhou L, Li B, Gao W, et al. Unsupervised Discovery of Discourse Relations for Eliminating Intra-sentence Polarity Ambiguities [C]//Proceedings of EMNLP 2011 (Oral presentation), Edinburgh, Scotland, July 27-31, 2011. 被引量:1
  • 5E Pitler, A Nenkova. Revisiting readability: A unified framework for predicting text quality[C]//Proceedings of EMNLP 2008: 186-195. 被引量:1
  • 6Ziheng Lin, Hwee Tou NG, Min-Yen Kan. Automati- cally Evaluating Text Coherence Using Discourse Rela- tions[C]//Proceedings of ACL-HLT: 997-1006. 被引量:1
  • 7Morris J, Hirst G. Lexical cohesion computed by the- saural relations as an indicator of the structure of text [J]. Computational Linguistics, 1991, 17(1):21-48. 被引量:1
  • 8Grosz Barbara J, Aravind K Joshi, Scott Weinstein. Centering: A Framework for Modelling the Local Co- herence of Discourse[J]. Computational Linguistics, 1995,21/2: 203-25. 被引量:1
  • 9Fillmore, Charles J. Frame semantics and the nature of language[J]. In Annals of the New York Academy of Sciences: Conference on the Origin and Developmentof Language and Speech, 1976, 280:20 - 32. 被引量:1
  • 10Schank, R C, A belson, R Scripts, Plans, Goals, and Understanding [M]. Hillsdale, N J: Earlbaum Assoc, 1977. 被引量:1

共引文献10

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 意见反馈