Machine learningDeep learning / NLP / CV

Prijenosno učenje sa sažimanjem teksta

Prijenosno učenje sa sažimanjem teksta prilagođava veliki jezični model pred-treniran na širokim tekstualnim korpusima — kao što su T5, BART ili PEGASUS — zadatku kondenziranja dokumenata u kraće, koherentne sažetke. Ponovnom uporabom naučenog lingvističkog znanja i finim podešavanjem na parovima izvornih dokumenata i referentnih sažetaka specifičnih za domenu, ovaj pristup postiže snažnu kvalitetu sažimanja uz skromne zahtjeve za označenim podacima.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

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

Izvori

  1. Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1–67. link
  2. Lewis, M., Liu, Y., Goyal, N., Ghahravi, M., Mohamed, A., Chen, D., Levy, O., & Zettlemoyer, L. (2020). BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 7871–7880). ACL. DOI: 10.18653/v1/2020.acl-main.703

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Transfer Learning with Neural Text Summarization. ScholarGate. https://scholargate.app/hr/deep-learning/transfer-learning-with-text-summarization

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

ScholarGateTransfer Learning with Text Summarization (Transfer Learning with Neural Text Summarization). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/transfer-learning-with-text-summarization · Skup podataka: https://doi.org/10.5281/zenodo.20539026