Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| GRU inayobadilika na Nyanja× | Transformer zinazobadilika na dhima (Domain-Adaptive Transformer - DAT)× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2016–present | 2019–2022 |
| Mwanzilishi≠ | Cho et al. (GRU, 2014); Ganin et al. (domain-adversarial framework, 2016) | Various (Vaswani et al. 2017 for Transformers; domain adaptation extensions emerged 2019–2022) |
| Aina≠ | Sequence model with domain adaptation | Pre-trained model fine-tuned with domain-shift adaptation |
| Chanzo asilia≠ | Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014 (pp. 1724–1734). Association for Computational Linguistics. link ↗ | 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 | DA-GRU, Domain-Adapted GRU, GRU with Domain Adaptation, Domain-Shift-Robust GRU | DAT, domain-adaptive Transformer, domain adaptation with Transformers, transfer-learning Transformer |
| Zinazohusiana≠ | 4 | 2 |
| Muhtasari≠ | Domain-Adaptive GRU combines the Gated Recurrent Unit architecture with domain adaptation techniques to train a sequence model on a labeled source domain and transfer it to a different but related target domain, reducing performance degradation caused by distribution shift. It is widely applied in NLP tasks such as cross-domain sentiment analysis, named entity recognition, and text classification where labeled target-domain data is scarce. | 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 ↗ |
|
|