Gradual Fine-Tuning for Low-Resource Domain Adaptation

Haoran Xu, Seth Ebner, Mahsa Yarmohammadi, Aaron Steven White, Benjamin Van Durme, Kenton Murray


Abstract
Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain. Such domain adaptation is typically done using one stage of fine-tuning. We demonstrate that gradually fine-tuning in a multi-step process can yield substantial further gains and can be applied without modifying the model or learning objective.
Anthology ID:
2021.adaptnlp-1.22
Volume:
Proceedings of the Second Workshop on Domain Adaptation for NLP
Month:
April
Year:
2021
Address:
Kyiv, Ukraine
Editors:
Eyal Ben-David, Shay Cohen, Ryan McDonald, Barbara Plank, Roi Reichart, Guy Rotman, Yftah Ziser
Venue:
AdaptNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
214–221
Language:
URL:
https://aclanthology.org/2021.adaptnlp-1.22
DOI:
Bibkey:
Cite (ACL):
Haoran Xu, Seth Ebner, Mahsa Yarmohammadi, Aaron Steven White, Benjamin Van Durme, and Kenton Murray. 2021. Gradual Fine-Tuning for Low-Resource Domain Adaptation. In Proceedings of the Second Workshop on Domain Adaptation for NLP, pages 214–221, Kyiv, Ukraine. Association for Computational Linguistics.
Cite (Informal):
Gradual Fine-Tuning for Low-Resource Domain Adaptation (Xu et al., AdaptNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.adaptnlp-1.22.pdf
Code
 fe1ixxu/Gradual-Finetune +  additional community code