语义检索系统中的查询语句扩展算法改进  

Improvement on Arithmetic of Query Expansion in Semantic Retrieval

作　　者：杨学兵[1,2] 钱蓉[2] 

机构地区：[1]南京大学计算机科学与技术系,江苏南京210093 [2]安徽工业大学计算机学院,安徽马鞍山243002

出　　处：《计算机技术与发展》2008年第12期1-3,7,共4页Computer Technology and Development

基　　金：安徽省自然科学基金重点资助项目(2004KJ053ZD)

摘　　要：查询扩展技术是在原有用户查询的基础上加入语义相关的新词,组成语义更准确的查询条件。文中对查询扩展算法中扩展词加权方法进行改进,提出一种基于初始用户查询意欲和词与词间语义关联性给扩展词加权的方法。根据此算法得到的扩展词权值不仅反映了该扩展词和原关键词间的关联性,还反映出该扩展词和查询关键词集合中所有元素的关联性。因此,可将基于语义树的查询扩展问题转换为扩展词权值wijs,o,p的计算,如何计算出权值wijs,o,p是文中的核心。实验证明,该算法提高了检索的查准率。Query expansion adds some new correlated words to original retrieval to make a more efficient query. In order to improve the way of adding the weight to the word in the query expansion, proposes a new way of adding the weight based on original query and the relation between a word and another. According to this arithmetic, it can get the weight which reflects not only the original word and expansive word but also the original query and expansive word. Therefore, the problem of query expansion can be converted into computing the value of ws,o,p^ij, the core of this paper is how to compute the value of ws,o,p^ij. The experimental result shows this arithmetic improve the accuracy of semantic retrieval.

关 键 词：语义相似度 语义关联度 查询扩展 语义检索 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]