Word embeddings for morphologically complex languages

2016
journal article
article
1
dc.abstract.enRecent 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.affiliationWydział Matematyki i Informatykipl
dc.contributor.authorJurdziński, Grzegorzpl
dc.date.accessioned2017-10-18T07:45:22Z
dc.date.available2017-10-18T07:45:22Z
dc.date.issued2016pl
dc.date.openaccess0
dc.description.accesstimew momencie opublikowania
dc.description.physical127-138pl
dc.description.versionostateczna wersja wydawcy
dc.description.volume25pl
dc.identifier.doi10.4467/20838476SI.16.010.6191pl
dc.identifier.eissn2083-8476pl
dc.identifier.issn1732-3916pl
dc.identifier.projectROD UJ / Ppl
dc.identifier.urihttps://ruj.uj.edu.pl/xmlui/handle/item/45271
dc.languageengpl
dc.language.containerengpl
dc.rightsDozwolony użytek utworów chronionych*
dc.rights.licenceInna otwarta licencja
dc.rights.urihttp://ruj.uj.edu.pl/4dspace/License/copyright/licencja_copyright.pdf*
dc.share.typeotwarte czasopismo
dc.subject.enmachine learningpl
dc.subject.enword embeddingspl
dc.subject.ennatural language processingpl
dc.subject.enmorphologypl
dc.subtypeArticlepl
dc.titleWord embeddings for morphologically complex languagespl
dc.title.journalSchedae Informaticaepl
dc.typeJournalArticlepl
dspace.entity.typePublication
dc.abstract.enpl
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.
dc.affiliationpl
Wydział Matematyki i Informatyki
dc.contributor.authorpl
Jurdziński, Grzegorz
dc.date.accessioned
2017-10-18T07:45:22Z
dc.date.available
2017-10-18T07:45:22Z
dc.date.issuedpl
2016
dc.date.openaccess
0
dc.description.accesstime
w momencie opublikowania
dc.description.physicalpl
127-138
dc.description.version
ostateczna wersja wydawcy
dc.description.volumepl
25
dc.identifier.doipl
10.4467/20838476SI.16.010.6191
dc.identifier.eissnpl
2083-8476
dc.identifier.issnpl
1732-3916
dc.identifier.projectpl
ROD UJ / P
dc.identifier.uri
https://ruj.uj.edu.pl/xmlui/handle/item/45271
dc.languagepl
eng
dc.language.containerpl
eng
dc.rights*
Dozwolony użytek utworów chronionych
dc.rights.licence
Inna otwarta licencja
dc.rights.uri*
http://ruj.uj.edu.pl/4dspace/License/copyright/licencja_copyright.pdf
dc.share.type
otwarte czasopismo
dc.subject.enpl
machine learning
dc.subject.enpl
word embeddings
dc.subject.enpl
natural language processing
dc.subject.enpl
morphology
dc.subtypepl
Article
dc.titlepl
Word embeddings for morphologically complex languages
dc.title.journalpl
Schedae Informaticae
dc.typepl
JournalArticle
dspace.entity.type
Publication
Affiliations

* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.