Näita lihtsat nimetuse kirjet

dc.contributor.authorAedmaa, Eleri
dc.date.accessioned2019-04-11T15:00:33Z
dc.date.available2019-04-11T15:00:33Z
dc.date.issued2019
dc.identifier.urihttp://datadoi.ee/handle/33/91
dc.identifier.urihttps://doi.org/10.15155/re-60
dc.description.abstractWord and multi-sense embedding for Estonian trained on lemmatized etTenTen: Corpus of the Estonian Web. Word embeddings are trained with word2vec. Sense embeddings are trained with SenseGram. Sense inventory is induced from word embeddings. Models were trained using various parameter settings. The values of architecture, number of dimensions, window size, minimum frequency threshold and number of iterations vary.en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectword embeddingsen_US
dc.subjectsense embeddingsen_US
dc.subjectEstonianen_US
dc.titlePretrained word and multi-sense embeddings for Estonianen_US
dc.typeinfo:eu-repo/semantics/dataseten_US


Failid selles nimetuses

Thumbnail

Nimetus asub järgmis(t)es andmekogumi(te)s:

Näita lihtsat nimetuse kirjet