计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (10): 120-123.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于概念图的汉语语义计算的研究与实现

张晓孪,王西锋   

  1. 宝鸡文理学院 计算机科学系,陕西 宝鸡 721007
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-04-01 发布日期:2011-04-01

Study and implementation of Chinese semantic computation based on conceptual graph

ZHANG Xiaoluan,WANG Xifeng   

  1. Department of Computer Science,Baoji University Arts & Sciences,Baoji,Shaanxi 721007,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-04-01 Published:2011-04-01

摘要: 中文信息处理的发展迫切需要加强汉语语义理论的研究,尤其是汉语语义表示形式和语义计算的研究。针对目前汉语语义计算方法的计算结果并不准确的问题,提出了一种基于概念图的汉语语义计算方法。该方法以“知网”为语义知识资源,以概念图为知识表示方法,把自然语言文本转化为概念图,通过概念图的匹配实现语义计算,以改善语义计算的效果。实验结果表明该方法对汉语语义计算是有效的。

关键词: 知网, 概念图, 语义计算, 相似度, 匹配

Abstract: The development of Chinese information processing requires strengthening Chinese semantic theory research urgently,especially Chinese semantic representation and semantic computation’s research.For the problem of Chinese semantic analysis method has the inaccurate result,the method of Chinese semantic computation based on conceptual graph is proposed.With HowNet as the semantic knowledge resource and conceptual graphs as knowledge representation method,it concerts the natural language text into conceptual graphs and realizes semantic commutation by way of conceptual graph matching,in order to improve the effects of the Chinese semantic analysis.The experimental results prove that it is effective to the Chinese semantic analysis.

Key words: HowNet, conceptual graph, semantic computation, similarity, matching