基于聚类和词组抽取的XML查询扩展  

Query Expansion Based on Clustering and Key Phrase Extraction for XML Data

作　　者：钟敏娟[1,2] 万常选[1,2] 焦贤沛[1,2] 

机构地区：[1]江西财经大学信息管理学院,南昌330013 [2]江西财经大学数据与知识工程江西省高校重点实验室,南昌330013

出　　处：《情报学报》2010年第4期597-604,共8页Journal of the China Society for Scientific and Technical Information

基　　金：国家自然科学基金项目（60763001 60803105）; 国家社会科学基金项目（07BTQ025）

摘　　要：查询扩展技术通过向初始查询请求加入相似或相关的词,组成更为准确的扩展查询表达式,来减少查询请求与相关文献在表达上的不匹配现象,改善检索性能。与传统的查询扩展不同,XML查询扩展不仅要对文档内容进行有效扩展,而且还要考虑结构扩展。本文提出了一种基于伪反馈的XML查询扩展方法,将初始检索结果聚类,获得与查询请求最为相关的文档簇,然后在文档簇中抽取词组,找到符合用户查询意图的扩展查询词组,并在扩展查询词组的基础上进行结构扩展,最终形成完整的“内容＋结构”的查询扩展表达式。相关实验结果表明,相对没有扩展的查询,所提方法具有更好的精度。Query expansion technology can reduce word mismatch between query and related documents,construct more precise query expression and improve retrieval result through adding similar or related terms to original query.Compared with traditional query expansion,XML query expansion is different from traditional query expansion,which expands not only to document content,but also structural expansion.In this paper,a method of XML query expansion based on pseudo-relevance feedback is proposed.It firstly performs clustering algorithm to original retrieval results for finding the most relate clusters to user＇ s query.Secondly,the technology of information extraction is used to gain expanded key phrases that can satisfy the user＇ s intention.Finally,structural expansion is made based on the expanded key phrases and a full-edged content-structure query is formalized.Experimental results show that the proposed method outperform original query in precision and obtain the better retrieval quality.

关 键 词：XML 伪反馈 聚类 扩展查询词组 结构查询扩展 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]