基于传递的语义相关度计算方法研究  

Algorithm for Semantic Relatedness Based on Transitivity

作　　者：裘江南[1] 李丽冬[1] 吴力文[1] 叶奋飞[1] 

机构地区：[1]大连理工大学管理学院信息管理系,大连116023

出　　处：《情报学报》2010年第4期749-758,共10页Journal of the China Society for Scientific and Technical Information

基　　金：国家社会科学基金（批准号：07CTQ006）

摘　　要：基于本体的语义相关度计算方法以概念在本体中的结构特征,如深度、密度,概念间的语义关系类型、路径等一系列因素为基础来度量概念间的语义相关度,缺乏对传递因素的考虑。本文通过基于本体的通用语义相关度计算方法的影响要素分析、传统方法的特点研究及语义传递规律的介绍,提出一种基于传递的语义相关度计算方法,并利用《知网》与传统方法基于人工判断进行效果比较,验证了新语义相关度计算方法的应用效果。Ontology-based algorithm of semantic relatedness is based on structure of ontology,such as depth and density, types of semantic relations between concepts,path and a number of other factors to measure semantic relations between concepts, but it ignores the factor of semantic transitivity between concepts.For this,based on analyses of influencing elements of common Ontology-based semantic relatedness algorithm,research on characteristics of the traditional methods and rules of semantic transitivity,a new measurement of semantic relatedness is proposed in the paper.In order to verify the application results,effect test of this new method is done comparing with human judging of traditional methods in HowNet.

关 键 词：语义相关 相关度计算 语义距离 语义传递 

分 类 号：H030[语言文字—语言学]