Comparer des méthodes

	Word2Vec affiné	Classification par BERT affiné
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2013 (Word2Vec); fine-tuning practice 2014–2016	2019
Auteur d'origine	Mikolov, T. et al. (Word2Vec); fine-tuning practice generalised by the NLP community post-2013	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI)
Type	Domain-adapted word embedding model	Pre-trained transformer fine-tuned for classification
Source fondatrice	Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. In Proceedings of ICLR 2013 Workshop.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
Alias	domain-adapted Word2Vec, continued-training Word2Vec, Word2Vec fine-tuning, W2V domain adaptation	BERT fine-tuning, BERT classifier, fine-tuned BERT, BERT sequence classification
Apparentées	6	5
Résumé	Fine-Tuned Word2Vec adapts a pre-trained Word2Vec model to a specific domain or task by continuing its training on domain-specific text. Rather than training embeddings from scratch, practitioners load general-purpose vectors (e.g., Google News embeddings) and run additional Skip-gram or CBOW epochs on domain corpora, shifting word representations toward domain-specific usage patterns.	Fine-Tuned BERT-based Classification adapts a pre-trained BERT transformer to a specific text classification task by adding a lightweight output layer and continuing gradient-based training on labelled examples. It consistently achieves near-state-of-the-art accuracy on sentiment analysis, topic categorisation, intent detection, and other NLP classification tasks with relatively small labelled datasets.