Skip to Main Content
Semantic similarity between two words is a fundamental issue for many natural language processing applications. The difficulty lies in that how to develop a computational method that is capable of generating satisfactory results close to what humans would perceive. In this paper, we proposed a novel approach to measure the semantic similarity between two English words by exploring the utility of HowNet, which is a valuable Chinese-English bilingual knowledge base. When compared with a benchmark set by human similarity judgment, the measures achieved by our algorithm are quite sound.
Date of Conference: 18-21 Nov. 2008