Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Klasyfikacja oparta na domenowo adaptowanym modelu BERT× | Klasyfikacja oparta na RoBERTa× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2019–2020 | 2019 |
| Twórca≠ | Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT | Liu, Y. et al. (Facebook AI Research / University of Washington) |
| Typ≠ | Domain-adaptive pre-training followed by supervised fine-tuning | Pre-trained transformer fine-tuned for sequence classification |
| Źródło pierwotne≠ | 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 ↗ | 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 ↗ |
| Inne nazwy | DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT | RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification |
| Pokrewne≠ | 6 | 5 |
| Podsumowanie≠ | 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. | RoBERTa-based Classification applies the RoBERTa pre-trained transformer — trained more robustly than BERT with dynamic masking and larger batches — to text categorisation tasks by adding a lightweight classification head on top of the [CLS] token representation and fine-tuning the entire model on labelled examples. It consistently matches or outperforms BERT on standard NLP benchmarks. |
| ScholarGateZbiór danych ↗ |
|
|