Comparer des méthodes

	Word2Vec	GloVe
Domaine	Fouille de textes	Fouille de textes
Famille	Process / pipeline	Process / pipeline
Année d'origine	2013	2014
Auteur d'origine	Tomas Mikolov et al.	Pennington, Socher & Manning
Type	Neural word-embedding model	Static word-embedding model
Source fondatrice	Mikolov, T., Chen, K., Corrado, G. & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space.	Pennington, J., Socher, R. & Manning, C. D. (2014). GloVe: Global Vectors for Word Representation. EMNLP.
Alias	word embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri	GloVe, global vectors, GloVe Kelime Gömülmeleri
Apparentées	4	3
Résumé	Word2Vec is a neural word-embedding technique introduced by Mikolov and colleagues in 2013 that maps each word in a text corpus to a dense numeric vector. Words that appear in similar contexts end up close together in the vector space, so the embeddings capture semantic similarity that can be measured arithmetically.	GloVe (Global Vectors for Word Representation) is a static word-embedding model introduced by Pennington, Socher and Manning (2014) that learns word vectors directly from global word-word co-occurrence statistics gathered across an entire corpus. The resulting vectors place semantically related words close together and perform strongly on semantic analogy tasks.