Paper: Word Vectors And Two Kinds Of Similarity

ACL ID P06-2110
Title Word Vectors And Two Kinds Of Similarity
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006

This paper examines what kind of similar- ity between words can be represented by what kind of word vectors in the vector space model. Through two experiments, three methods for constructing word vec- tors, i.e., LSA-based, cooccurrence-based and dictionary-based methods, were com- pared in terms of the ability to represent two kinds of similarity, i.e., taxonomic similarity and associative similarity. The result of the comparison was that the dictionary-based word vectors better re- flect taxonomic similarity, while the LSA- based and the cooccurrence-based word vectors better reflect associative similarity.