Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Uainishaji wa BERT unaobadilika kulingana na kikoa× | Transformer zinazobadilika na dhima (Domain-Adaptive Transformer - DAT)× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2019–2020 | 2019–2022 |
| Mwanzilishi≠ | Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT | Various (Vaswani et al. 2017 for Transformers; domain adaptation extensions emerged 2019–2022) |
| Aina≠ | Domain-adaptive pre-training followed by supervised fine-tuning | Pre-trained model fine-tuned with domain-shift adaptation |
| Chanzo asilia≠ | 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 ↗ | Ni, J., Hernandez Abrego, G., Constant, N., Ma, J., Hall, K., Cer, D., & Yang, Y. (2021). Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models. Findings of ACL 2022. arXiv:2108.08877. link ↗ |
| Majina mbadala | DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT | DAT, domain-adaptive Transformer, domain adaptation with Transformers, transfer-learning Transformer |
| Zinazohusiana≠ | 6 | 2 |
| Muhtasari≠ | 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. | A Domain-Adaptive Transformer (DAT) is a Transformer-based model — such as BERT or ViT — extended with an explicit domain-alignment objective so that learned representations transfer well from a labeled source domain to a different, often unlabeled, target domain. The approach combines the powerful representation capacity of Transformers with domain adaptation techniques such as adversarial training or contrastive alignment to minimise domain shift. |
| ScholarGateSeti ya data ↗ |
|
|