Measuring Semantic Similarity between Words Using HowNet

Semantic similarity between 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 how humans perceive. In this paper, a novel method is proposed to measure semantic similarity between words using HowNet, which is a renowned Chinese-English bilingual knowledge base. Furthermore, a Chinese thesaurus is used to improve the similarity measuring. Theoretically, our method can be used in many languages while in this case it is applied for English and Chinese. Experiments on English and Chinese word pairs show that our method are closest to human similarity judgments when compared to the major state-of-the-art methods.