So sánh phương pháp

	Mô hình hóa chủ đề có thể giải thích	Mô hình Chủ đề NMF
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2003–2020s	1999
Người khởi xướng	Community practice (Blei et al. seminal; explainability extensions 2010s–present)	Lee, D. D. & Seung, H. S.
Loại	Unsupervised topic discovery + interpretability layer	Matrix factorization / unsupervised topic model
Công trình gốc	Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993–1022.	Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791.
Tên gọi khác	XTM, interpretable topic modeling, transparent topic modeling, explainable LDA	NMF, Non-negative Matrix Factorization, NMF for Topic Modeling, NNMF Topic Model
Liên quan	6	4
Tóm tắt	Explainable Topic Modeling combines unsupervised topic discovery — such as LDA, NMF, or neural variants like BERTopic — with interpretability tools (top-word lists, coherence scores, SHAP, attention weights) that make the learned topics transparent, auditable, and communicable to domain experts and stakeholders beyond the modeling team.	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.