基于WordNet的概念语义相似度研究

Concept Semantic Similarity Researching Based on WordNet

WordNet是普林斯顿大学的一个研究项目,目标是建立英语词汇及其词法关系的数据库,这将促进数据互通性、信息搜寻和检索、自动推理和自然语言处理。基于该共享知识本体,提出了一种计算两概念语义相似度的方法。根据该方法实现了一个计算程序模块,并将计算结果同人类的主观判断进行了比较,验证了该方法的有效性。该研究工作可以在面向Web的知识检索领域中得到应用,还可以为本体的相关研究提供一定的理论基础。

The Suggested Upper Merged Ontology （WORDNET） is an effort by the Standard Upper Ontology Working Group of IEEE. The goal is to develop the Standard Upper Ontology, and it will encourage interoperability, information searching, automatic reasoning and natural language processing. In this paper we propose a method for computing the semantic similarity of two concepts, and it is implemented as a computing module. Finally, we compare the results got from the program with the judgments of subjects. Through this experiment, the method is proved valid. Our research can be applied in the field of knowledge searching, and it provides a basis of theory for the relative research on ontology.