Abstract

This paper presents a method for measuring the semantic similarity between words. The previous work on words semantic similarity measure have focused on either knowledge based or word embedding based. However semantic similarity between words do not perform well within specific domains. Therefore in this paper we introduce a word semantic similarity measure namely KVEC that was created by the synergistic union of word embedding based and knowledge graph based semantic similarity methods. Through experiments performed on proverbial word similarity dataset, we show that KVEC semantic similarity method whose maximum correlation coefficient reached 0.818, which outperform both, knowledge based method and word embedding method training on corpus.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call