Porównaj metody

	Klasyfikacja oparta na domenowo adaptowanym modelu BERT	Uczenie maszynowe z klasyfikacją opartą na BERT
Dziedzina	Uczenie głębokie	Uczenie głębokie
Rodzina	Machine learning	Machine learning
Rok powstania	2019–2020	2019 (BERT); transfer learning paradigm established circa 2010
Twórca	Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (BERT); Pan, S. J. & Yang, Q. (transfer learning survey)
Typ	Domain-adaptive pre-training followed by supervised fine-tuning	Pre-trained transformer fine-tuned for 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.	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.
Inne nazwy	DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT	BERT fine-tuning for classification, BERT transfer learning classifier, pre-trained BERT classifier, BERT downstream classification
Pokrewne	6	4
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.	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.