« Word2vec » : différence entre les versions

Version du 26 février 2018 à 20:47

Domaine

Catégorie Démo Apprentissage profond

Définition

Termes privilégiés

Anglais

word2vec

word2vec is an algorithm and tool to learn word embeddings by trying to predict the context of words in a document. The resulting word vectors have some interesting properties, for example vector('queen') ~= vector('king') - vector('man') + vector('woman'). Two different objectives can be used to learn these embeddings: The Skip-Gram objective tries to predict a context from on a word, and the CBOW objective tries to predict a word from its context.

Version du 26 février 2018 à 20:47 (voir la source) Pitpitt (discussion \| contributions) (Page créée avec « == Domaine == catégorie:Démo Catégorie Démo Catégorie:Apprentissage profond Apprentissage profond == Définition == == Termes privilégiés ==... »)		Version du 26 février 2018 à 20:47 (voir la source) Pitpitt (discussion \| contributions) Aucun résumé des modifications Modification suivante →
Ligne 18 :		Ligne 18 :


	word2vec		'''word2vec'''

	word2vec is an algorithm and tool to learn word embeddings by trying to predict the context of words in a document. The resulting word vectors have some interesting properties, for example vector('queen') ~= vector('king') - vector('man') + vector('woman'). Two different objectives can be used to learn these embeddings: The Skip-Gram objective tries to predict a context from on a word, and the CBOW objective tries to predict a word from its context.		word2vec is an algorithm and tool to learn word embeddings by trying to predict the context of words in a document. The resulting word vectors have some interesting properties, for example vector('queen') ~= vector('king') - vector('man') + vector('woman'). Two different objectives can be used to learn these embeddings: The Skip-Gram objective tries to predict a context from on a word, and the CBOW objective tries to predict a word from its context.