Machine learningDeep learning / NLP / CV

Samostalno-nadgledane ugradnje rečenica

Samostalno-nadgledane ugradnje rečenica obučavaju neuronske enkodere da mapiraju rečenice u gusti vektorski prostor bez potrebe za ručno označenim parovima. Konstruisanjem pozitivnih primera automatski – na primer, prolaskom iste rečenice kroz dropout dvaput – i korišćenjem kontrastivnih ciljeva, model uči semantički bogate reprezentacije koje se dobro prenose na zadatke sličnosti, pretraživanja i klasifikacije.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 6894–6910. DOI: 10.18653/v1/2021.emnlp-main.552
  2. 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), 3982–3992. DOI: 10.18653/v1/D19-1410

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Self-supervised Learning for Sentence Embeddings. ScholarGate. https://scholargate.app/sr/deep-learning/self-supervised-sentence-embeddings

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateSelf-supervised Sentence Embeddings (Self-supervised Learning for Sentence Embeddings). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/self-supervised-sentence-embeddings · Skup podataka: https://doi.org/10.5281/zenodo.20539026