摘要
为提高信息检索的查全率和查准率,提出改进的本体语义相似度计算方法,利用本体中概念语义相似度对检索结果文档的分值进行重新计算,过滤掉与原始查询相关度较小的文档。给出定义查询扩展中的迭代参数,减少进行扩展的次数,提高查询效率。利用开源工具Jena,Lucene进行文本语义检索测试,验证该方法的可行性和有效性。
To enhance information retrieval recall and precision, this paper proposes an improved method of calculating ontology semantic similarity. To filter out the document which has smaller related degree with origin query, the scores of search results document are re-calculated by use of ontology semantic similarity. Put forward a definition of the iterative query expansion parameters, reducing the number of expansion and improve the efficiency of query. By using open source tools Jena, Lucene for text semantic retrieval test, the proposed method is verified feasibility and effectiveness.
出处
《计算机工程》
CAS
CSCD
北大核心
2010年第12期55-57,共3页
Computer Engineering
基金
安徽省自然科学基金资助项目(050420204)
安徽省高校自然科学研究基金资助项目(2006kj055B)
关键词
语义检索
本体
语义相似度
查询扩展
文档分值
information retrieval
ontology
semantic similarity
query expansion
document scores