Comparer des méthodes

	Auto-apprentissage avec Word2Vec	FastText	GloVe	Réseau de neurones récurrent
Domaine	Apprentissage profond	Apprentissage profond	Fouille de textes	Apprentissage profond
Famille	Machine learning	Machine learning	Process / pipeline	Machine learning
Année d'origine	2013	2016	2014	1986–1990
Auteur d'origine	Mikolov, T., Chen, K., Corrado, G., & Dean, J.	Joulin, A.; Bojanowski, P.; Grave, E.; Mikolov, T. (Facebook AI Research)	Pennington, Socher & Manning	Rumelhart, D. E.; Elman, J. L.
Type	Self-supervised neural word embedding	Subword embedding model and linear text classifier	Static word-embedding model	Sequential neural network
Source fondatrice	Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. In Proceedings of the International Conference on Learning Representations (ICLR 2013).	Joulin, A., Grave, E., Bojanowski, P. & Mikolov, T. (2017). Bag of Tricks for Efficient Text Classification. In Proceedings of EACL 2017, Short Papers, pp. 427–431. ACL.	Pennington, J., Socher, R. & Manning, C. D. (2014). GloVe: Global Vectors for Word Representation. EMNLP.	Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.
Alias	Word2Vec, word embeddings, Skip-gram model, CBOW model	fastText, fast text, subword embedding, character n-gram embedding	GloVe, global vectors, GloVe Kelime Gömülmeleri	RNN, Elman network, Jordan network, simple recurrent network
Apparentées	3	2	3	3
Résumé	Word2Vec is a shallow neural network model introduced by Mikolov et al. (2013) that learns dense vector representations of words from large unlabeled text corpora using self-supervised objectives. By training a model to predict surrounding context words (Skip-gram) or a target word from its context (CBOW), it captures rich semantic and syntactic regularities in continuous vector space without any manual annotation.	FastText is a word embedding and text classification framework developed by Facebook AI Research (Joulin, Bojanowski, Grave, and Mikolov, 2016–2017) that represents each word as the sum of its character n-gram vectors, allowing it to construct meaningful representations for unseen and morphologically rich words and to perform near state-of-the-art text classification orders of magnitude faster than deep neural network alternatives.	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.	A Recurrent Neural Network (RNN) is a class of neural network designed to process sequential data by maintaining a hidden state that carries information across time steps. Introduced in its modern form by Rumelhart et al. (1986) and further shaped by Elman (1990), RNNs became the dominant architecture for sequence modelling in NLP, speech, and time-series analysis before the rise of attention-based models.