Please use this identifier to cite or link to this item:
Title: Comparing distributional semantic models for identifying groups of semantically related words
Author: Kovatchev, Venelin
Salamó Llorente, Maria
Martí Antonin, M. Antònia
Keywords: Tractament del llenguatge natural (Informàtica)
Natural language processing (Computer science)
Issue Date: 15-Sep-2016
Publisher: Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN)
Abstract: 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.
Note: Reproducció del document publicat a:
It is part of: Procesamiento del lenguaje natural , 2016, num. 57, p. 109-116
ISSN: 1135-5948
Appears in Collections:Articles publicats en revistes (Filologia Catalana i Lingüística General)

Files in This Item:
File Description SizeFormat 
666326.pdf263.86 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.