方法证据记录
Domain-adaptive transformer
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.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Domain-Adaptive Transformer (DAT)
分类方法记录 · ml-model / deep-learning
- 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. · URL
- Guo, J., Shah, D., & Barzilay, R. (2022). Multi-Source Domain Adaptation with Mixture of Experts. In Proceedings of EMNLP 2018. arXiv:1809.02060. · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。