Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Adaptacyjna do domeny klasyfikacja oparta na RoBERTa× | Klasyfikacja oparta na domenowo adaptowanym modelu BERT× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania | 2019–2020 | 2019–2020 |
| Twórca≠ | Liu et al. (RoBERTa); Gururangan et al. (domain-adaptive pretraining) | Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT |
| Typ≠ | Pre-trained transformer with domain-adaptive pretraining and task fine-tuning | Domain-adaptive pre-training followed by supervised fine-tuning |
| Źródło pierwotne≠ | Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692. link ↗ | Gururangan, S., Marasovic, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020). Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 8342–8360. DOI ↗ |
| Inne nazwy | DA-RoBERTa, domain-adapted RoBERTa classifier, RoBERTa domain adaptation, domain-specific RoBERTa fine-tuning | DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT |
| Pokrewne≠ | 5 | 6 |
| Podsumowanie≠ | Domain-adaptive RoBERTa-based classification extends the RoBERTa transformer by first continuing its masked-language-model pretraining on a domain-specific corpus before fine-tuning for a classification task. This two-stage adaptation bridges the gap between general web-crawled training data and specialized fields such as biomedical, legal, or scientific text, consistently outperforming standard RoBERTa fine-tuning when target-domain text is available. | Domain-adaptive BERT-based classification extends the standard fine-tuning pipeline by first continuing BERT's masked-language-model pre-training on a large corpus of in-domain unlabeled text, then fine-tuning the adapted model on labeled examples for the target classification task. This two-stage approach closes the vocabulary and distributional gap between BERT's general pre-training corpus and specialized domains such as biomedicine, law, finance, or social-media text. |
| ScholarGateZbiór danych ↗ |
|
|