基于本体的语义检索方法

Semantic retrieval method based on ontology

为有效解决本体查询扩展的语义边界问题,提出一种基于本体和局部共现的查询扩展方法。计算概念在本体中的语义相似度和局部文档中的相关度,构成概念之间总的关联度来筛选扩展词;在此基础上,设计一个扩展词权重的计算方法,考虑原查询词的重要程度以及扩展词与原查询词的关系,改进查询与文档相关度的计算方法。实验结果表明,在设计的语义检索系统中,该方法在保证查全率的基础上能有效提高查准率。

To solve the semantic boundary problem of ontology query expansion effectively,the method of query expansion based on ontology and local co-occurrence was proposed.The semantic similarity in the ontology and the relevance in the local documents were computed for concepts.The overall correlation between concepts was composed to select expansion words.Based on that,the calculation method of expansion words weight was presented.The importance of the original query words and the relationship between the expansion words and the original query words were considered.And the calculation method of relevance between query and document was improved.Experimental results show that,in the design of semantic retrieval system,the precision is effectively improved using the method based on guaranteeing the recall.