基于概念格理论的语义相似度模型研究及验证  

Research of Semantic Similarity Computing Model and Validation Based on Concept Lattice

作　　者：张小红[1] 

机构地区：[1]河南财政税务高等专科学校信息工程系,河南郑州451464

出　　处：《郑州大学学报（工学版）》2011年第5期80-83,共4页Journal of Zhengzhou University（Engineering Science）

基　　金：河南省科技攻关计划项目(102102210532)

摘　　要：将语义相似度计算模型定义为域、概念、属性组成的三维空间模型,并结合领域本体集,从概念格理论的角度考虑了该模型对语义相似度计算的影响.该模型通过对不同的向量加不同的权值来调节其对语义相似度计算的贡献,使计算结果达到最优,从而提高语义相似度计算的准确度.实验结果表明,与单方面计算相似度的方法相比,该方法能有效地提高语义相似度计算的查全率和查准率.In this paper,the computing model of semantic similarity is defined as a three-dimensional model consisting of domain,concept and property.At the same time,according to the domain-specific ontology set,from the perspective of the theory of concept lattice,the paper studies the impacts of this model on the semantic similarity computing.This method assigns different weights to different features to adjust the contributions of each feature to the semantic similarity computing model in order to achieve optimal results and improve the accuracy.Experiments show that this method,compared with the methods of other computing similarity,can effectively improve the recall and precision of semantic similarity calculation.

关 键 词：语义相似度 概念格 领域 概念 属性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]