방법 비교

	준지도 비음수 행렬 분해 (NMF) 토픽 모델	문장 임베딩
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2001 (NMF); semi-supervised variants from ~2010s	2015–2019
창시자	Lee & Seung (NMF); semi-supervised extensions by Jagarlamudi et al. and others	Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019)
유형	Matrix factorization with supervision	Representation learning / embedding
원전	Lee, D. D., & Seung, H. S. (2001). Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, 13, 556–562.	Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3980–3990.
별칭	SS-NMF, guided NMF, constrained NMF topic model, seed-guided NMF	sentence vectors, sentence representations, SBERT, semantic sentence encoding
관련	6	4
요약	Semi-supervised Non-negative Matrix Factorization (NMF) Topic Model extends unsupervised NMF by incorporating user-provided seed words or label constraints to steer discovered topics toward domain-relevant themes. It factorizes a document-term matrix into interpretable non-negative components while respecting lexical priors, yielding coherent, application-aligned topics even from modest corpora.	Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines.