Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Doménově adaptivní sumarizace textu× | Přenosové učení s sumarizací textu× | |
|---|---|---|
| Obor | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2019–2021 | 2019–2020 |
| Tvůrce≠ | Multiple contributors; domain adaptation methods consolidated via transformer-era NLP (c. 2019–2021) | Raffel et al. (T5); Lewis et al. (BART) |
| Typ≠ | Domain adaptation of sequence-to-sequence neural summarization | Transfer learning applied to sequence-to-sequence summarization |
| Původní zdroj≠ | 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 ↗ | 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 ↗ |
| Další názvy | domain-adapted summarization, domain-specific summarization, cross-domain summarization, DA-summarization | pretrained summarization model, fine-tuned summarization, TL-summarization, neural abstractive summarization via transfer learning |
| Příbuzné≠ | 6 | 4 |
| Shrnutí≠ | Domain-adaptive text summarization fine-tunes or adapts a pre-trained sequence-to-sequence language model on a target domain corpus so that summaries conform to domain-specific vocabulary, style, and factual constraints. It bridges the gap between general-purpose summarization models trained on news or web data and specialized domains such as biomedical literature, legal documents, scientific papers, or financial reports. | Transfer Learning with Text Summarization adapts a large language model pre-trained on broad text corpora — such as T5, BART, or PEGASUS — to the task of condensing documents into shorter, coherent summaries. By reusing learned linguistic knowledge and fine-tuning on domain-specific pairs of source documents and reference summaries, this approach achieves strong summarization quality with modest labeled data requirements. |
| ScholarGateDatová sada ↗ |
|
|