Concept Name Similarity Calculation Based on WordNet and Ontology

Concept name similarity calculation between ontologies is the basis of ontology mapping. Many concept name words are polysemous, but in traditional word similarity algorithms, the similarity between the most similar senses of two words was regarded as the word similarity. It were ignored that the true meanings of concept names in the context, which resulted in falling of the precision of similarity calculation and ontology mapping. A new algorithm was presented in this paper: The true meaning of hypernym concept of an ontology concept and the comment of this concept were seen as two conceptual features. The conceptual WordNet sense the most similar to the features in all senses was determined as the true sense of this concept in ontology context. Each of the two features can generate a corresponding concept sense determination method and a kind of concept name similarity. At last, the weighted sum of the two kinds of similarities was seen as the final concept name similarity. The experimental result showed that our algorithm outperforms other existing algorithms. The ambiguity of the concept name words can be eliminated, and the precision of both of concept name similarity calculation and ontology mapping can be increased dramatically.