Source-Free Unsupervised Domain Adaptation for Question Answering via Prompt-Assisted Self-learning

Maxwell Yin, Boyu Wang, Charles Ling


Abstract
This work addresses source-free domain adaptation (SFDA) for Question Answering (QA), wherein a model trained on a source domain is adapted to unlabeled target domains without additional source data. Existing SFDA methods only focus on the adaptation phase, overlooking the impact of source domain training on model generalizability. In this paper, we argue that source model training itself is also critical for improving the adaptation performance and stability. To this end, we investigate the role of prompt learning as an effective method to internalize domain-agnostic QA knowledge, which can be integrated into source training. After source training, an interactive self-learning strategy is proposed to further fine tune both model and prompt in the model adaptation phase. This leads to the Prompt-Assisted Self-Adaptive Learning (PASAL), an innovative SFDA approach for QA. Empirical evaluation on four benchmark datasets shows that PASAL surpasses existing methods in managing domain gaps and demonstrates greater stability across various target domains, validating the significance of source domain training for effective domain adaptation.
Anthology ID:
2024.findings-naacl.44
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
700–713
Language:
URL:
https://aclanthology.org/2024.findings-naacl.44
DOI:
Bibkey:
Cite (ACL):
Maxwell Yin, Boyu Wang, and Charles Ling. 2024. Source-Free Unsupervised Domain Adaptation for Question Answering via Prompt-Assisted Self-learning. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 700–713, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Source-Free Unsupervised Domain Adaptation for Question Answering via Prompt-Assisted Self-learning (Yin et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.44.pdf
Copyright:
 2024.findings-naacl.44.copyright.pdf