방법 비교

	NMF 토픽 모델	BERT 기반 분류
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	1999	2019
창시자	Lee, D. D. & Seung, H. S.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language)
유형	Matrix factorization / unsupervised topic model	Pre-trained language model with fine-tuning
원전	Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics.
별칭	NMF, Non-negative Matrix Factorization, NMF for Topic Modeling, NNMF Topic Model	BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS
관련	4	4
요약	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.	BERT-based Classification fine-tunes Google's Bidirectional Encoder Representations from Transformers model on a labelled text dataset, replacing the generic pre-trained head with a task-specific classification layer. It exploits deep bidirectional context from hundreds of millions of pre-trained parameters to deliver state-of-the-art accuracy on short- and medium-length text classification tasks with relatively modest amounts of labelled data.