Don't Stop Pretraining: Adapt Language Models to Domains and Tasks

Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A. Smith
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the domain of a target task. We present a study across four domains (biomedical and computer science publications, news, and reviews) and eight classification tasks, showing that a second phase of pretraining indomain (domain-adaptive pretraining) leads to
more » ... e gains, under both high-and low-resource settings. Moreover, adapting to the task's unlabeled data (task-adaptive pretraining) improves performance even after domain-adaptive pretraining. Finally, we show that adapting to a task corpus augmented using simple data selection strategies is an effective alternative, especially when resources for domain-adaptive pretraining might be unavailable. Overall, we consistently find that multiphase adaptive pretraining offers large gains in task performance. References Roee Aharoni and Yoav Goldberg. 2020. Unsupervised domain clusters in pretrained language models. In ACL.
doi:10.18653/v1/2020.acl-main.740 fatcat:2yk5xnaigjdo7bpy6n3l32ef44