词语相似度计算方法分析

摘要

词语相似度计算是自然语言处理、智能检索、文档聚类、文档分类、自动应答、词义排歧和机器翻译等很多领域的基础研究课题。词语相似度计算在理论研究和实际应用中具有重要意义。本文对词语相似度进行总结,分别阐述了基于大规模语料库的词语相似度计算方法和基于本体的词语相似度计算方法,重点对后者进行详细分析。最后对两类方法进行简单对比,指出各自优缺点。%Word Similarity computing is basic research of natural language processing,intelligent information retrieval,document clustering,document classification,automatic answering,word sense disambiguation and machine translation.Word similarity computing has an important significance in theoretical research and practical applications.In this paper,described the large scale corpus-based word similarity calculation method and ontology-based word similarity calculation method,pay attention to the latter.Comparison of the two types of methods,pointed out the respectively advantages and disadvantages.