基于相关术语群的中文查询扩展  

Chinese Query Expansion Based on Related Term Group

作　　者：涂新辉[1] 罗景[1] 

机构地区：[1]武汉科技大学计算机学院,武汉430065

出　　处：《计算机与数字工程》2008年第1期29-31,36,共4页Computer & Digital Engineering

摘　　要：查询词语和文档中词语的不匹配是影响文本信息检索效果的一个关键因素。查询扩展技术可以在一定程度上解决这种词的不匹配问题,然而,实验表明,通常简单的查询扩展并不能稳定地提高中文信息检索的检索精度。利用自动构建的相关术语群来进行查询扩展以提高中文检索的效果。在NTCIR中文信息检索测试集上进行的实验表明,相对于传统的查询扩展方法,在检索效果上取得了平均24.5%的提高。Term mismatch between queries and documents is a fundamental problem in Chinese Information Retrieval(IR),which affects the effectiveness of retrieval results.Query expansion in IR can deal with this kind of problem in some degree.However,experiments show that the common query expansion in IR cannot get steady retrieval results.This paper proposes a novel method to improve the performance of Chinese information retrieval systems by expanding queries using automatically acquired related term groups.Compared with results of the traditional relevance feedback technique,experiments show that our method can get statistically significant improvement.

关 键 词：中文信息检索 查询扩展 术语抽取 相关术语群 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]