A WordNet-based semantic similarity measurement combining edge-counting and information content theory

Semantic similarity measuring between words can be applied to many applications, such as Artificial Intelligence, Information Processing, Medical Care and Linguistics. In this paper, we present a new approach for semantic similarity measuring which is based on edge-counting and information content theory. Specifically, the proposed measure nonlinearly transforms the weighted shortest path length between the compared concepts to achieve the semantic similarity results, and the relation between parameters and the correlation value is discussed in detail. Experimental results show that the proposed approach not only achieves high correlation value against human ratings but also has better distribution characteristics of the correlation coefficient compared with several related works in the literature. In addition, the proposed method is computationally efficient due to the simplified ways of weighting the shortest path length between the concept pairs.