作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2010, Vol. 36 ›› Issue (21): 65-66,70. doi: 10.3969/j.issn.1000-3428.2010.21.023

• 软件技术与数据库 • 上一篇    下一篇

基于句法和语义信息的问句特征提取方法

许 莉1,王大玲2,夏秀峰1   

  1. (1. 沈阳航空工业学院计算机学院,沈阳 110136;2. 东北大学信息科学与工程学院,沈阳 110004)
  • 出版日期:2010-11-05 发布日期:2010-11-03
  • 作者简介:许 莉(1978-),女,讲师、硕士,主研方向:文本挖掘;王大玲,教授、博士、博士生导师;夏秀峰,教授、博士
  • 基金资助:
    国家自然科学基金资助项目(60573090);辽宁省自然科学基金资助项目(20062032) 

Question Features Exaction Method Based on Syntactic and Semantic Information

XU Li1, WANG Da-ling2, XIA Xiu-feng1   

  1. (1. School of Computer, Shenyang Institute of Aeronautical Engineering, Shenyang 110136, China; 2. School of Information Science and Engineering, Northeastern University, Shenyang 110004, China)
  • Online:2010-11-05 Published:2010-11-03

摘要: 在分析当前中文问答系统中问句分析技术的基础上,提出一种基于句法结构和语义信息的问题特征提取方法。利用依存句法分析出问句的主干,从语义信息角度分析问句主干从而提取出问句的特征词,并用改进贝叶斯算法进行问题分类。实验证明,该特征提取方法能提高问题分类的准确性。

关键词: 问答系统, 特征提取, 句法结构, 语义信息

Abstract: This paper analyzes the current question parsing techniques in Question Answering(QA), and proposes a question feature exaction method based on syntactic structure and semantic information. The method parses question trunks based on syntax structure, then extracts characteristics of question from the semantic information point of view and uses modified Bayesian algorithm in question classification. Experiments show that this method can raise the accuracy of the question classification.

Key words: Question Answering(QA) system, feature exaction, syntactic structure, semantic information

中图分类号: