Comparer des méthodes

	Modélisation thématique faiblement supervisée	Modélisation thématique semi-supervisée
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2012–2017	2009
Auteur d'origine	Jagarlamudi, Daume & Udupa; Gallagher et al. (CorEx)	Ramage, D.; Andrzejewski, D.; and related NLP community
Type	Weakly supervised probabilistic topic model	Probabilistic graphical model (supervised/constrained extension of LDA)
Source fondatrice	Jagarlamudi, J., Daume III, H., & Udupa, R. (2012). Incorporating Lexical Priors into Topic Models. Proceedings of EACL 2012, 204–213.	Ramage, D., Hall, D., Nallapati, R., & Manning, C. D. (2009). Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora. Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, 248–256. Association for Computational Linguistics.
Alias	guided topic modeling, seed-guided topic model, constrained topic modeling, seeded LDA	semi-supervised LDA, labeled LDA, seed-guided topic modeling, constrained topic model
Apparentées	5	3
Résumé	Weakly supervised topic modeling incorporates lightweight domain knowledge — typically seed words or soft constraints — into a probabilistic topic model to steer discovered topics toward researcher-meaningful themes. It sits between fully unsupervised LDA and supervised classifiers, requiring far less annotation than the latter while producing more interpretable and domain-aligned topics than the former.	Semi-supervised topic modeling extends unsupervised topic models such as LDA by incorporating partial human supervision — seed words, labeled documents, or must-link/cannot-link constraints — to steer discovered topics toward meaningful, domain-relevant categories while still exploiting the large unlabeled corpus for statistical strength.