Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Classification basée sur BERT et adaptée au domaine× | Classification par BERT affiné× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2019–2020 | 2019 |
| Auteur d'origine≠ | Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI) |
| Type≠ | Domain-adaptive pre-training followed by supervised fine-tuning | Pre-trained transformer fine-tuned for classification |
| Source fondatrice≠ | 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 ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186. DOI ↗ |
| Alias | DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT | BERT fine-tuning, BERT classifier, fine-tuned BERT, BERT sequence classification |
| Apparentées≠ | 6 | 5 |
| Résumé≠ | 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. | Fine-Tuned BERT-based Classification adapts a pre-trained BERT transformer to a specific text classification task by adding a lightweight output layer and continuing gradient-based training on labelled examples. It consistently achieves near-state-of-the-art accuracy on sentiment analysis, topic categorisation, intent detection, and other NLP classification tasks with relatively small labelled datasets. |
| ScholarGateJeu de données ↗ |
|
|