摘要
跨语言检索是一种重要的信息检索手段之一。为了提高跨语言检索效率,采用语义扩展的方法,通过分析其设计思想和工作流程,构建出一种基于语义扩展的跨语言自动检索模型,重点对其语义扩展、知识库和结果聚类等设计进行了阐述,提出了语义理解切分法的分词方法,采用了Single-Pass算法进行聚类,实验结果表明,该模型能有效提高跨语言检索的查全率和查准率。
The Cross - language retrieval is an important method of information retrieval. In order to improve the cross - language retrieval efficiency, it adapts the method of semantic extension. By analyzing the design idea and workflow, it builds a kind of cross- language automatic retrieval model based on semantic extension. Focusing on its semantic extension, knowledge base and expounding the result clustering design, the semantic understanding segmentation method of word segmentation method is proposedand adapts the Single- Pass clustering algorithm. The experimental results show that this model can effectively improve the cross- language retrieval recall and precision.
出处
《现代情报》
CSSCI
2014年第1期155-158,共4页
Journal of Modern Information
关键词
跨语言信息检索
语义扩展
分词
CLIR （Cross - Language Information Retrieval）
semantic extension
segmentation
