ScholarGate
Msaidizi
Machine learningDeep learning / NLP / CV

Muhtasari wa Muktadha-Ubadilifu

Muhtasari wa muktadha-ubadilifu hurekebisha au kuendana na lugha iliyofunzwa awali ya modeli ya lugha ya mpangilio-hadi-mpangilio kwenye mkusanyiko wa data wa muktadha lengwa ili muhtasari uzingatie msamiati, mtindo, na vikwazo vya ukweli vya muktadha maalum. Inajaza pengo kati ya modeli za muhtasari wa madhumuni ya jumla zilizofunzwa kwenye habari au data ya wavuti na muktadha maalum kama vile fasihi ya kibiolojia, hati za kisheria, karatasi za kisayansi, au ripoti za kifedha.

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.

Vyanzo

  1. Fabbri, A. R., KryŜiński, W., McCann, B., Xiong, C., Socher, R., & Radev, D. (2021). SummEval: Re-evaluating Summarization Evaluation. Transactions of the Association for Computational Linguistics, 9, 391–409. DOI: 10.1162/tacl_a_00373
  2. Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020). On Faithfulness and Factuality in Abstractive Summarization. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp. 1906–1919. DOI: 10.18653/v1/2020.acl-main.173

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Domain-adaptive Text Summarization (Domain Adaptation for Abstractive and Extractive Summarization). ScholarGate. https://scholargate.app/sw/deep-learning/domain-adaptive-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
ScholarGateDomain-adaptive Text Summarization (Domain-adaptive Text Summarization (Domain Adaptation for Abstractive and Extractive Summarization)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/domain-adaptive-text-summarization · Seti ya data: https://doi.org/10.5281/zenodo.20539026