领域本体中概念间语义相关度的概率估计  

Probability estimation for semantic association on domain ontology

作　　者：田萱[1] 李冬梅[1] 

机构地区：[1]北京林业大学信息学院,北京100083

出　　处：《计算机工程与应用》2011年第27期136-140,143,共6页Computer Engineering and Applications

基　　金：中央高校基本科研业务费专项资金(No.YX2011-30);北京林业大学新进教师科研启动基金(No.BLX2w8019)

摘　　要：根据贝叶斯定理提出一种衡量领域本体中概念间语义相关度的概率模型。该模型定义在不同语义关系之上,基于极大似然估计法利用语义距离来对语义关系进行参数估计。并在此基础给出一种计算任意两个概念之间语义相关度的方法。公开数据集上的实验结果表明该方法估计出的概念语义相关度具有相当的有效性,应用在语义查询扩展中可明显提高检索效果。A probability model based on Bayesian principles is given to measure the semantic association from a concept to its direct-related concept in domain ontology.The model is based on different semantic relationships,and is estimated according to maximum likelihood estimation.Semantic distance is used to estimate semantic relationships in estimating period.Based on the proposed model,a method to measure semantic association of any two concepts in ontology is given.Experiment results of semantic retrieval on open data show that semantic query expansion performs better than classic semantic query expansion.

关 键 词：领域本体 语义关系 语义相关度 语义距离 概率估计 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]