一种基于语料的词汇语义相似度认知算法  

A Cognition Measurement of Word Similarity Based on a Specific Subject Corpus

作　　者：吴华 罗顺 孙伟晋 WU Hua;LUO Shun;SUN Weijin(Shanghai General Recognition Technology Institute,Shanghai 201112)

机构地区：[1]上海通用识别技术研究所,上海201112

出　　处：《计算机与数字工程》2019年第2期300-303,共4页Computer & Digital Engineering

摘　　要：词汇的语义相似度计算是信息检索、自然语言处理、推荐系统等技术的基础。事实上,词汇可能因其语境或语料的不同,语义的相似度千差万别。论文通过提取词汇的上下文语境特征,构建了一种基于特定语料的词汇的语义相似度计算模型。实验结果表明,该算法有较好的准确率和较强的领域敏感性,取得了令人满意的结果。Word similarity measurement is the basis for techniques of information retrieval,natural language processing,rec. ommender systems,and so on. Actually,word similarity may be entirely different because of its context or subject. The paper intro. duces a cognition measurement of word similarity based on a specific subject corpus through word's context feature. An experimental result indicates that the measurement method can achieve good precision rate and field sensitivity.

关 键 词：文本分析 自然语言处理 领域预料 语义相似度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]