摘要
传统的模糊集合模型基于词词关联矩阵来实现模糊检索,词词关联矩阵只考虑语词在文献内部的同时出现。本文提出了一个基于相似性叙词表的模糊集合模型,考虑语词与查询之间的相似性,并将查询扩展包含在此模型中,从而在一定程度上提高了检索性能。
Traditional fuzzy set model is based on term-term correlation matrix for fuzzy retrieval, which only considers term co-occurrence within documents. The paper presents a fuzzy set model based on similarity thesaurus which considers the similarity between term and query. And we add the query expansion into the model. To some extent, the retrieval performance is improved.
出处
《计算机科学》
CSCD
北大核心
2008年第9期201-202,229,共3页
Computer Science
基金
江苏省科学技术厅项目(BA2005001)资助
