Порівняння методів

	Самокероване тематичне моделювання	Тема моделі NMF
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2020–2023	1999
Автор методу	Various (Miao et al. 2016 for neural topic models; self-supervised objectives widely adopted 2020–2023)	Lee, D. D. & Seung, H. S.
Тип	Self-supervised neural topic model	Matrix factorization / unsupervised topic model
Основоположне джерело	Wu, X., Li, C., Zhu, Y., & Miao, Y. (2023). Effective Neural Topic Modeling with Embedding Clustering Regularization. Proceedings of the 40th International Conference on Machine Learning (ICML 2023), PMLR 202, 37335–37357.	Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791.
Інші назви	SSL topic model, self-supervised neural topic model, contrastive topic modeling, self-supervised LM-based topic modeling	NMF, Non-negative Matrix Factorization, NMF for Topic Modeling, NNMF Topic Model
Пов'язані	5	4
Підсумок	Self-supervised topic modeling combines the interpretable topic discovery of classical topic models with self-supervised learning objectives — such as contrastive loss, masked language modeling, or reconstruction — to learn coherent, semantically rich topics from unlabeled text without human-annotated labels. It bridges classical probabilistic topic models and modern representation learning, yielding topics better aligned with contextual meaning.	Non-negative Matrix Factorization (NMF) is an unsupervised matrix decomposition method that discovers latent topics in a text corpus by factoring a document-term matrix into two non-negative matrices — one encoding topic-word weights, the other document-topic weights. The non-negativity constraint yields parts-based, additive representations that tend to produce clean, interpretable topics.