Word embeddings for morphologically complex languages

Show full item record

dc.contributor.author	Jurdziński, Grzegorz	pl
dc.date.accessioned	2017-10-18T07:45:22Z
dc.date.available	2017-10-18T07:45:22Z
dc.date.issued	2016	pl
dc.identifier.issn	1732-3916	pl
dc.identifier.uri	https://ruj.uj.edu.pl/xmlui/handle/item/45271
dc.language	eng	pl
dc.rights	Dozwolony użytek utworów chronionych	*
dc.rights.uri	http://ruj.uj.edu.pl/4dspace/License/copyright/licencja_copyright.pdf	*
dc.title	Word embeddings for morphologically complex languages	pl
dc.type	JournalArticle	pl
dc.description.physical	127-138	pl
dc.abstract.en	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.	pl
dc.subject.en	machine learning	pl
dc.subject.en	word embeddings	pl
dc.subject.en	natural language processing	pl
dc.subject.en	morphology	pl
dc.description.volume	25	pl
dc.identifier.doi	10.4467/20838476SI.16.010.6191	pl
dc.identifier.eissn	2083-8476	pl
dc.title.journal	Schedae Informaticae	pl
dc.language.container	eng	pl
dc.affiliation	Wydział Matematyki i Informatyki	pl
dc.subtype	Article	pl
dc.rights.original	OTHER; otwarte czasopismo; ostateczna wersja wydawcy; w momencie opublikowania; 0	pl
dc.identifier.project	ROD UJ / P	pl
.pointsMNiSW	[2016 B]: 11