ScholarGate
Msaidizi
Machine learningDeep learning / NLP / CV

Muhtasari wa Maandishi Ulioboreshwa

Muhtasari wa Maandishi Ulioboreshwa hubadilisha mfumo mkuu wa awali uliotayarishwa wa mfuatano-hadi-mfuatano — kama vile BART, T5, au PEGASUS — ili kuzalisha muhtasari mfupi wa hati kwa kutoa mafunzo kwenye jozi za (hati, muhtasari) maalum kwa kikoa. Njia hii hutoa muhtasari wenye ufasaha na uaminifu zaidi kuliko mbinu za dondoo au za jumla kwa kutumia maarifa yaliyohifadhiwa katika mabilioni ya tokeni za awali za mafunzo.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

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

+1 more

Vyanzo

  1. Zhang, J., Zhao, Y., Saleh, M., & Liu, P. J. (2020). PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization. Proceedings of the 37th International Conference on Machine Learning (ICML), 119, 11328–11339. link
  2. Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), 7871–7880. DOI: 10.18653/v1/2020.acl-main.703

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Fine-Tuned Pre-trained Sequence-to-Sequence Model for Text Summarization. ScholarGate. https://scholargate.app/sw/deep-learning/fine-tuned-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

Imerejelewa na

ScholarGateFine-Tuned Text Summarization (Fine-Tuned Pre-trained Sequence-to-Sequence Model for Text Summarization). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/fine-tuned-text-summarization · Seti ya data: https://doi.org/10.5281/zenodo.20539026