大众标注系统中基于本体的语义检索模型研究  

Study on Ontology-based Semantic Retrieval Model in Folksonomy

作　　者：窦永香[1] 何继媛[1] 刘东苏[1] 

机构地区：[1]西安电子科技大学经济管理学院,西安710071

出　　处：《情报学报》2012年第4期381-389,共9页Journal of the China Society for Scientific and Technical Information

基　　金：本文获国家自然科学基金项目（71003080）及中央高校基本科研业务费专项资金（72104234）资助.

摘　　要：针对大众标注系统中信息检索缺乏语义性的问题,引入本体,建立了基于系统专用本体的语义检索模型,包括7个功能模块：资源标注模块、标签推荐模块、提问处理模块、语义检索模块、结果处理模块、用户反馈处理模块以及本体构建和管理模块,阐述了各个模块的功能.详细分析了以查询扩展为基础的检索策略和过程.重点研究了系统专用本体的构建,提出一种通过分析标签间隐含的语义关系及WordNet辅助生成本体的方法,并进行了模拟实验验证.Aiming at the problem of lacking semantic retrieval in Folksonomy system, ontology is introduced, and semantic retrieval model based on specialized ontology is built in this paper. The model consists of seven modules ： resource labeling module, tag recommendation module, query process module, semantic search module, result process module, user feedback process module and ontology construct and manage module, and the function of each module is stated. Search strategy based on query expansion and search process is analyzed in detail. We also research the construction of specialized ontology, and propose a method for generating ontology by analyzing connotative semantic relation between tags and WordNet assisted, and design experiment to prove the validity of the method.

关 键 词：大众标注 本体 本体构建 语义检索 

分 类 号：G250.76[文化科学—图书馆学]