Abstract
Neural networks are known to be data hungry and domain sensitive, but it is nearly impossible to obtain large quantities of labeled data for every domain we are interested in. This necessitates the use of domain adaptation strategies. One common strategy encourages generalization by aligning the global distribution statistics between source and target domains, but one drawback is that the statistics of different domains or tasks are inherently divergent, and smoothing over these differences can lead to sub-optimal performance. In this paper, we propose the framework of Domain Differential Adaptation (DDA), where instead of smoothing over these differences we embrace them, directly modeling the difference between domains using models in a related task. We then use these learned domain differentials to adapt models for the target task accordingly. Experimental results on domain adaptation for neural machine translation demonstrate the effectiveness of this strategy, achieving consistent improvements over other alternative adaptation strategies in multiple experimental settings.- Anthology ID:
- D19-5606
- Volume:
- Proceedings of the 3rd Workshop on Neural Generation and Translation
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong
- Editors:
- Alexandra Birch, Andrew Finch, Hiroaki Hayashi, Ioannis Konstas, Thang Luong, Graham Neubig, Yusuke Oda, Katsuhito Sudoh
- Venue:
- NGT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 59–69
- Language:
- URL:
- https://aclanthology.org/D19-5606
- DOI:
- 10.18653/v1/D19-5606
- Cite (ACL):
- Zi-Yi Dou, Xinyi Wang, Junjie Hu, and Graham Neubig. 2019. Domain Differential Adaptation for Neural Machine Translation. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 59–69, Hong Kong. Association for Computational Linguistics.
- Cite (Informal):
- Domain Differential Adaptation for Neural Machine Translation (Dou et al., NGT 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/D19-5606.pdf
- Code
- zdou0830/DDA