首页 | 本学科首页   官方微博 | 高级检索  
     

基于句法分析和答案分类的中文问答系统
引用本文:孙昂,江铭虎,贺一帆,陈林,袁保宗.基于句法分析和答案分类的中文问答系统[J].电子学报,2008,36(5):833-839.
作者姓名:孙昂  江铭虎  贺一帆  陈林  袁保宗
作者单位:1. 清华大学人文学院计算语言学实验室,北京 100084;2. 北京交通大学信息科学 研究所,北京 100044;3. 清华大学心理学与认知科学中心,北京 100084
摘    要:本文根据疑问词和谓语的距离信息对问句进行细致的句型分析,然后对答句进行浅层句法分析,在此基础上,抽取出问题特征集、答句特征集和组合特征集作为分类特征,引入最大熵模型和支持向量机训练答案抽取分类器.基于不同特征组合训练得到的分类器在五类事实性问题上进行了测试,其F值分别达到70.87%和85.75%.

关 键 词:中文问答系统  句法分析  答案抽取  最大熵模型  支持向量机  
文章编号:0372-2112(2008)05-0833-07
收稿时间:2007-10-24
修稿时间:2007年10月24

Chinese Question Answering Based on Syntax Analysis and Answer Classification
SUN Ang,JIANG Ming-hu,HE Yi-fan,CHEN Lin,YUAN Bao-zong.Chinese Question Answering Based on Syntax Analysis and Answer Classification[J].Acta Electronica Sinica,2008,36(5):833-839.
Authors:SUN Ang  JIANG Ming-hu  HE Yi-fan  CHEN Lin  YUAN Bao-zong
Affiliation:1. Lab of Computational Linguistics,School of Humanities and Social Sciences,Tsinghua University,Beijing 100084,China;2. Institute of Information Science,Beijing Jiaotong University,Beijing 100044,China;3. Center for Psychology and Cognitive Science,Tsinghua University,Beijing 100084,China
Abstract:This paper first conducts rigorous sentence pattern analysis of questions based on the distance between question word and predicate,and then conduct shallow parse of answer candidate sentences.Based on the analysis,we extract question feature set;answer sentence feature set and combined feature set as our features for answer classification.Then we apply maximum entropy model and support vector machine to these features to train answer classifiers.The F-Measures of the two classifiers' experiment conducted o...
Keywords:Chinese question answering  syntax analysis  answer extraction  maximum entropy model(MEM)  support vector machine(SVM)  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《电子学报》浏览原始摘要信息
点击此处可从《电子学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号