Comparer des méthodes

	Word2Vec faiblement supervisé	Embeddings de phrases faiblement supervisées
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2013–2016	2016–2019
Auteur d'origine	Mikolov et al. (Word2Vec); weak supervision framework: Ratner et al.	Ratner et al. (weak supervision framework); Reimers & Gurevych (sentence embeddings)
Type	Word embedding with noisy/programmatic labels	Representation learning under weak supervision
Source fondatrice	Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems, 26.	Ratner, A., De Sa, C., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29.
Alias	WS-Word2Vec, weakly-supervised word embeddings, weak-label Word2Vec, semi-noisy Word2Vec	WS sentence embeddings, noisy-label sentence representation learning, weakly supervised sentence representation, distant-supervision sentence embeddings
Apparentées	6	6
Résumé	Weakly Supervised Word2Vec trains Word2Vec-style embeddings using automatically generated, noisy, or heuristic labels rather than costly manual annotation. By leveraging labeling functions, distant supervision, or keyword-based rules to assign soft labels, the approach enables domain-adapted word representations even when large manually annotated corpora are unavailable.	Weakly supervised sentence embeddings train dense sentence representations using noisy, heuristic, or programmatically generated labels instead of costly human annotation. Labeling functions — rules, distant supervision signals, or lightweight classifiers — supply approximate supervision that a label model aggregates into probabilistic labels, which then guide the sentence encoder to produce task-useful representations at scale.