Comparer des méthodes

	Résumé de texte faiblement supervisé	Apprentissage auto-supervisé
Domaine	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2015–2020	2018–2020
Auteur d'origine	Multiple independent research groups (NLP community, 2010s–2020s)	LeCun, Y. and community (formalized ~2018–2020)
Type	Semi-supervised / weakly supervised NLP training paradigm	Representation learning paradigm
Source fondatrice	Amplayo, R. K., & Lapata, M. (2020). Unsupervised Opinion Summarization with Noisy Autoencoder. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 1934–1945.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
Alias	weak supervision summarization, distantly supervised summarization, noisy-label summarization, pseudo-label summarization	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Apparentées	1	3
Résumé	Weakly supervised text summarization trains abstractive or extractive summarization models without manually annotated reference summaries. Instead of costly human labels, it exploits weak signals — heuristic rules, distant supervision, noisy automatic labels, or self-supervised objectives — to guide sequence-to-sequence or transformer models toward producing coherent, concise summaries of input documents.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.