Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Modeliranje tema× | Ugrađivanje rečenica× | |
|---|---|---|
| Područje | Duboko učenje | Duboko učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 1999–2003 | 2015–2019 |
| Tvorac≠ | Hofmann, T. (pLSA, 1999); Blei, D. M., Ng, A. Y., & Jordan, M. I. (LDA, 2003) | Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019) |
| Vrsta≠ | Unsupervised generative probabilistic model | 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. link ↗ | 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. DOI ↗ |
| Drugi nazivi | Latent Semantic Analysis, probabilistic topic modeling, topic discovery, thematic modeling | sentence vectors, sentence representations, SBERT, semantic sentence encoding |
| Srodne≠ | 5 | 4 |
| Sažetak≠ | Topic Modeling is a family of unsupervised probabilistic techniques for discovering latent thematic structure in large text collections. By learning which words tend to co-occur, models such as Latent Dirichlet Allocation (LDA) automatically surface coherent topics — each represented as a distribution over vocabulary — without requiring labelled data. | 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. |
| ScholarGateSkup podataka ↗ |
|
|