基于关键词语义扩展的检索策略  

Retrieval strategy based on semantic expansion of keywords

作　　者：杜金洋[1,2] 易禾[3] 杨春[1,2] 

机构地区：[1]四川师范大学计算机科学学院,成都610101 [2]四川师范大学可视化计算与虚拟现实四川省重点实验室,成都610066 [3]四川师范大学计算机信息网络中心,成都610066

出　　处：《计算机应用》2009年第6期1575-1577,共3页journal of Computer Applications

基　　金：国家973计划项目(2008CB317110)

摘　　要：传统基于关键字匹配检索策略由于关键字的机械字符匹配和一词多义问题很容易造成漏检和错检。为此,从领域本体概念入手,结合关键字检索的特点,提出一种基于关键词语义扩展的检索策略。策略使用领域本体描述的语义结构扩展关键字匹配范围,避免完全机械的字符匹配造成的漏检,从而提高检索的查全率。在此基础上,利用领域本体中语义相关度过滤检索无关结果,以提高检索的查准率,并根据检索结果与本体语义相关度算法排序。Traditional retrieval strategy based on keyword-matching is facing unavoidable bottleneck because of mechanical characters matching and polysemy problems. A retrieval strategy based on domain ontology and semantic expansion of keywords was proposed. On the one hand, the domain ontology concept structure was used to expand the retrieval area; on the other hand, a method was presented to filter the irrelevant results. In this way, both the recall ratio and the precision ratio could be improved simultaneously. After that, an algorithm of sorting the retrieval results by the similarity between ontology and result was given.

关 键 词：领域本体 扩展 查全率 查准率 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]