期刊文献+

改进的基于模式匹配的答案抽取方法 被引量:1

Improved Answer Extraction Method Based on Pattern Matching
原文传递
导出
摘要 开放领域的问答系统是自然语言处理领域中具有挑战性的研究方向。答案抽取是问答系统的关键,在基于模式匹配的答案抽取方法中,答案是借助于问题的答案模式抽取得到,因此,答案模式的评价对候选答案排序及答案的最终选择起着决定性的作用。参照传统的答案模式评价方法,提出一种改进的模式评价方法,分别在传统和改进两种答案模式评价方法下进行了答案抽取实验。实验结果表明应用改进的答案模式评价方法,答案抽取性能明显提高。 The question-and-answer system in open domain is a challenging research orientation in natural language processing field. Answer extraction is the key of the question-and-answer system. In the answer extraction method based on pattern matching, the answer is extracted by means of the pattern of the answer to the question. Therefore, the evaluation of the pattern of the answer plays a decisive role in the ranking of candidate answers and final selection of answers. By reference to the traditional evaluation method, we put forward a new method of pattern evaluation, that is, carrying out answer extraction experiment separately in the traditional and improved pattern evaluation methods. The experimental results show that the improved pattern evaluation method improves the performance of answer extraction markedly.
出处 《情报理论与实践》 CSSCI 北大核心 2009年第9期105-108,共4页 Information Studies:Theory & Application
关键词 问答系统 模式匹配 答案抽取 question-and-answer system pattern matching answer extraction
  • 相关文献

参考文献7

二级参考文献46

  • 1张宇,刘挺,文勖.基于改进贝叶斯模型的问题分类[J].中文信息学报,2005,19(2):100-105. 被引量:47
  • 2余正涛,樊孝忠,郭剑毅.基于支持向量机的汉语问句分类[J].华南理工大学学报(自然科学版),2005,33(9):25-29. 被引量:20
  • 3余正涛,樊孝忠,宋丽哲,高盛祥.汉语问答系统答案提取方法研究[J].计算机工程,2006,32(3):183-185. 被引量:8
  • 4杨沐昀 赵铁军 于浩.自底向上的汉语句法标注体系设计与实践[A].黄昌宁主编.自然语言理解与机器翻译[C].南京清华大学出版社,2001.160—166.
  • 5C.D. Manning H. Schutze Foundations of statistical natural language processing The MIT Press. Cambridge, Massachusetts, London, England,.
  • 6T. L. Booth and R. A. Thompson. Applying Probability Measures to Abstract Languages. IEEE Transactions on Computers, 1973,C- 22(5), :442-450.
  • 7E, Black F. Jelinek J. Lafferty D, Magerman Towerds history-based grammars: using richer models for probabilistic parsing in Proc.ACL'93,Columbus,OH,1993:31-37
  • 8David M. Magerman. Natural Language Parsing as Statistical Pattern Recognition. Ph.D. thesis Stanford University. 1994.
  • 9Marcus, Mitehell Deterministic Parsing and Description Theory in P. Whitelock, M. Wood, H. Somers & P.Bennett (eds) Linguistie Theory and Computer Applications, New York, Academic Press, 1980:69-112.
  • 10Steve Abney. Rapid incremental parsing with repair. In Proceedings of the 6th New OED Conference:Electronic Text Research, 1990:1-9.

共引文献31

同被引文献11

  • 1北京语言学院句型研究小组.现代汉语基本句型(续完).世界汉语教学,1991,1:23-29.
  • 2MOREO A, EISMAN E M, CASTRO J L, et al. Learning reg- ular expressions to template-based FAQ retrieval systems [ J ]. Knowledge-Based Systems, 2013, 53: 108-128.
  • 3ZHANG G, JIANG T, BIE R, et al. The architecture of ProMe instant question answering system [ C ]. Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2013 International Conference on. IEEE, 2013: 237-242.
  • 4SHAW R S, TSAO C F, WU P W. A study of the application of ontology to an FAQ automatic classification system [ J]. Ex- pert Systems with Applications, 2012, 39 ( 14 ) : 11593-11606.
  • 5YENSJ, WUY C, YANGJ C, et al.A support vector ma- chine-based context-ranking model for question answering [ J ]. Information Sciences, 2013, 224: 77-87.
  • 6FIGUEROA A, ATKINSON J. Contextual language models for ranking answers to natural language definition questions [ J ]. Computational Intelligence, 2012, 28 (4): 528-548.
  • 7QIU Xipeng, ZHANG Qi, HUANG Xuanjing. FudanNLP: a toolkit for Chinese natural language processing [ C ] //Pro- ceedings of Annual Meeting of the Association for Computational Linguistics (ACL), 2013.
  • 8刘小明,樊孝忠,刘里.融合事件信息的复杂问句分析方法[J].华南理工大学学报(自然科学版),2011,39(7):140-145. 被引量:7
  • 9熊大平,王健,林鸿飞.一种基于LDA的社区问答问句相似度计算方法[J].中文信息学报,2012,26(5):40-45. 被引量:18
  • 10张巍,陈俊杰.信息熵方法及在中文问题分类中的应用[J].计算机工程与应用,2013,49(10):129-131. 被引量:5

引证文献1

二级引证文献1

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