Measuring Semantic Similarity Based on WordNet

Abstract

Semantic similarity between concepts is a fundamental problem and plays an important role in many applications of artificial intelligence, knowledge sharing and Web mining. In this paper, a new measure based on semantic ontology database WordNet is proposed which combines information content-based measure and the edge-counting techniques to measure semantic similarity. "PART-OF" and "IS-A" hierarchical relations' influence are considered on the semantic similarity in this paper. Breadth-first search is used to find the shortest path between two concepts. The similarity of hiberarchy and superposition are calculated respectively. WordNet3.0 is employed; JWNL1.4.1 is used to operate WordNet. According to the experiment against a benchmark set by human similarity judgment, our measure achieves a better result.