计算术语间语义相似度的混合方法  

Combined measurement approach for semantic similarity of terms

作　　者：魏韡[1,2] 向阳[1] 陈千[1] 

机构地区：[1]同济大学电子与信息工程学院,上海201804 [2]井冈山大学信息科学与传媒学院,江西吉安343009

出　　处：《计算机应用》2010年第6期1668-1670,共3页journal of Computer Applications

基　　金：国家自然科学基金资助项目(70771077);国家863计划项目(2008AA04Z106);上海市科委制造业信息化专项基金资助项目(08DZ1122303)

摘　　要：提出一种基于有向无环图和内在信息量的计算语义相似度的方法。首先计算出两个术语基于所在有向无环图的子图,再分别计算两个子图的交集和并集。用内在信息量方法计算出两个子图的交集和并集包含的节点的内在信息量,再计算出交集的节点内在信息量之和以及并集的节点内在信息量之和,将两者的比值作为两个术语的语义相似度。实验结果表明,该方法具有较高的准确度。Measuring semantic similarities of terms is a key issue in many research fields.This paper proposed a method based on the Directed Acyclic Graphs （DAG） of terms and the intrinsic information content of terms to measure the semantic similarities of terms.It first calculated the sub-graphs of two terms based on the directed acyclic graph,and then calculated the intersection and union of the sub-graphs.The semantic similarity of two terms is the ratio of the total intrinsic information content of terms in the intersection to the total intrinsic information content of terms in the union.The experimental results show that the method has a higher degree of accuracy.

关 键 词：语义相似度 内在信息量 有向无环图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]