The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation

Xin Su, Yiyun Zhao, Steven Bethard


Abstract
This paper describes our systems for negation detection and time expression recognition in SemEval 2021 Task 10, Source-Free Domain Adaptation for Semantic Processing. We show that self-training, active learning and data augmentation techniques can improve the generalization ability of the model on the unlabeled target domain data without accessing source domain data. We also perform detailed ablation studies and error analyses for our time expression recognition systems to identify the source of the performance improvement and give constructive feedback on the temporal normalization annotation guidelines.
Anthology ID:
2021.semeval-1.56
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Alexis Palmer, Nathan Schneider, Natalie Schluter, Guy Emerson, Aurelie Herbelot, Xiaodan Zhu
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
458–466
Language:
URL:
https://aclanthology.org/2021.semeval-1.56
DOI:
10.18653/v1/2021.semeval-1.56
Bibkey:
Cite (ACL):
Xin Su, Yiyun Zhao, and Steven Bethard. 2021. The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 458–466, Online. Association for Computational Linguistics.
Cite (Informal):
The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation (Su et al., SemEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.56.pdf