Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Transfer Learning avec Classification basée sur BERT× | Classification basée sur RoBERTa× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2019 (BERT); transfer learning paradigm established circa 2010 | 2019 |
| Auteur d'origine≠ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (BERT); Pan, S. J. & Yang, Q. (transfer learning survey) | Liu, Y. et al. (Facebook AI Research / University of Washington) |
| Type≠ | Pre-trained transformer fine-tuned for classification | Pre-trained transformer fine-tuned for sequence classification |
| Source fondatrice≠ | 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, 4171–4186. Association for Computational Linguistics. 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 ↗ |
| Alias | BERT fine-tuning for classification, BERT transfer learning classifier, pre-trained BERT classifier, BERT downstream classification | RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification |
| Apparentées≠ | 4 | 5 |
| Résumé≠ | Transfer Learning with BERT-based Classification adapts a large transformer language model, pre-trained on massive text corpora, to a target classification task by fine-tuning its weights on labeled examples. The pre-trained representations encode rich syntactic and semantic knowledge, enabling high accuracy even when the labeled dataset is small. | 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. |
| ScholarGateJeu de données ↗ |
|
|