TY - GEN
T1 - A Comparison of Strategies for Source-Free Domain Adaptation
AU - Su, Xin
AU - Zhao, Yiyun
AU - Bethard, Steven
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free domain adaptation. We take algorithms that traditionally assume access to the source-domain training data-active learning, self-training, and data augmentation-and adapt them for source-free domain adaptation. Then we systematically compare these different strategies across multiple tasks and domains. We find that active learning yields consistent gains across all SemEval 2021 Task 10 tasks and domains, but though the shared task saw successful self-trained and data augmented models, our systematic comparison finds these strategies to be unreliable for source-free domain adaptation.
AB - Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free domain adaptation. We take algorithms that traditionally assume access to the source-domain training data-active learning, self-training, and data augmentation-and adapt them for source-free domain adaptation. Then we systematically compare these different strategies across multiple tasks and domains. We find that active learning yields consistent gains across all SemEval 2021 Task 10 tasks and domains, but though the shared task saw successful self-trained and data augmented models, our systematic comparison finds these strategies to be unreliable for source-free domain adaptation.
UR - http://www.scopus.com/inward/record.url?scp=85139066960&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85139066960&partnerID=8YFLogxK
U2 - 10.18653/v1/2022.acl-long.572
DO - 10.18653/v1/2022.acl-long.572
M3 - Conference contribution
AN - SCOPUS:85139066960
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 8352
EP - 8367
BT - ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
A2 - Muresan, Smaranda
A2 - Nakov, Preslav
A2 - Villavicencio, Aline
PB - Association for Computational Linguistics (ACL)
T2 - 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
Y2 - 22 May 2022 through 27 May 2022
ER -