Comparing Distributional Semantics Models for identifying groups of semantically related words

Venelin Kovatchev, Maria Salamó, M. Antònia Martí


Distributional Semantic Models (DSM) are growing in popularity in Computational Linguistics. DSM use corpora of language use to automatically induce formal representations of word meaning. This article focuses on one of the applications of DSM: identifying groups of semantically related words. We compare two models for obtaining formal representations: a well known approach (CLUTO) and a more recently introduced one (Word2Vec). We compare the two models with respect to the PoS coherence and the semantic relatedness of the words within the obtained groups. We also proposed a way to improve the results obtained by Word2Vec through corpus preprocessing. The results show that: a) CLUTO outperformsWord2Vec in both criteria for corpora of medium size; b) The preprocessing largely improves the results for Word2Vec with respect to both criteria.

Texto completo: