Usporedite metode

	Samonadzirani LDA model tema	Ugrađivanje rečenica
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2003 (LDA); self-supervised variants from 2020	2015–2019
Tvorac	Blei, D. M., Ng, A. Y., Jordan, M. I. (LDA); self-supervised extension by multiple authors (2020s)	Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019)
Vrsta	Probabilistic generative model with self-supervised pretraining	Representation learning / embedding
Temeljni izvor	Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993–1022.	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.
Drugi nazivi	SSL-LDA, self-supervised topic modeling, self-supervised LDA, contrastive LDA	sentence vectors, sentence representations, SBERT, semantic sentence encoding
Srodne	6	4
Sažetak	Self-supervised LDA combines the probabilistic generative framework of Latent Dirichlet Allocation with self-supervised pretraining signals — such as masked-word prediction or contrastive document objectives — to guide topic discovery without requiring hand-labeled training data. The result is topic representations that are simultaneously grounded in distributional statistics and enriched by language structure learned from raw text.	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.