Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Prijenosno učenje sa sažimanjem teksta× | Preneseno učenje s prepoznavanjem imenovanih entiteta× | |
|---|---|---|
| Područje | Duboko učenje | Duboko učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 2019–2020 | 2010 / 2019 |
| Tvorac≠ | Raffel et al. (T5); Lewis et al. (BART) | Pan & Yang (transfer learning); Devlin et al. (BERT-based NER fine-tuning) |
| Vrsta≠ | Transfer learning applied to sequence-to-sequence summarization | Supervised sequence labeling via pretrained encoder fine-tuning |
| Temeljni izvor≠ | 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 ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics. DOI ↗ |
| Drugi nazivi | pretrained summarization model, fine-tuned summarization, TL-summarization, neural abstractive summarization via transfer learning | TL-NER, Fine-Tuned NER, Pretrained Model NER, BERT NER |
| Srodne≠ | 4 | 5 |
| Sažetak≠ | 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. | Transfer Learning with Named Entity Recognition (NER) adapts a large pretrained language model — such as BERT, RoBERTa, or a domain-specific encoder — to the task of identifying and classifying named entities (persons, locations, organizations, dates, etc.) in text. By reusing rich linguistic representations learned from massive corpora, this approach requires only modest labeled NER data while achieving state-of-the-art span detection and classification accuracy. |
| ScholarGateSkup podataka ↗ |
|
|