Word embeddings for morphologically complex languages

Bibliographic description

punktacja MEiN [2016 B]: 11

title:	Word embeddings for morphologically complex languages
author:	Jurdziński Grzegorz
journal title:	Schedae Informaticae
volume:	25
date of publication :	2016
pages:	127-138
ISSN:	1732-3916
eISSN:	2083-8476
DOI:	10.4467/20838476SI.16.010.6191
language:	English
journal language:	English
abstract in English:	Recent methods for learning word embeddings, like GloVe orWord2Vec, succeeded in spatial representation of semantic and syntactic relations. We extend GloVe by introducing separate vectors for base form and grammatical form of a word, using morphosyntactic dictionary for this. This allows vectors to capture properties of words better. We also present model results for word analogy test and introduce a new test based on WordNet.
keywords in English:	machine learning, word embeddings, natural language processing, morphology
affiliation:	Wydział Matematyki i Informatyki
type:	journal article
subtype:	academic paper