Abstract
This work connects language model adaptation with concepts of machine learning theory. We consider a training setup with a large out-of-domain set and a small in-domain set. We derive how the benefit of training a model on either set depends on the size of the sets and the distance between their underlying distributions. We analyze how out-of-domain pre-training before in-domain fine-tuning achieves better generalization than either solution independently. Finally, we present how adaptation techniques based on data selection, such as importance sampling, intelligent data selection and influence functions, can be presented in a common framework which highlights their similarity and also their subtle differences.- Anthology ID:
- 2022.acl-long.264
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3802–3813
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.264
- DOI:
- 10.18653/v1/2022.acl-long.264
- Cite (ACL):
- David Grangier and Dan Iter. 2022. The Trade-offs of Domain Adaptation for Neural Language Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3802–3813, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- The Trade-offs of Domain Adaptation for Neural Language Models (Grangier & Iter, ACL 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.acl-long.264.pdf