Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation

Sangwon Yoon, Yanghoon Kim, Kyomin Jung


Abstract
Source-free domain adaptation is an emerging line of work in deep learning research since it is closely related to the real-world environment. We study the domain adaption in the sequence labeling problem where the model trained on the source domain data is given. We propose two methods: Self-Adapter and Selective Classifier Training. Self-Adapter is a training method that uses sentence-level pseudo-labels filtered by the self-entropy threshold to provide supervision to the whole model. Selective Classifier Training uses token-level pseudo-labels and supervises only the classification layer of the model. The proposed methods are evaluated on data provided by SemEval-2021 task 10 and Self-Adapter achieves 2nd rank performance.
Anthology ID:
2021.semeval-1.55
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
452–457
Language:
URL:
https://aclanthology.org/2021.semeval-1.55
DOI:
10.18653/v1/2021.semeval-1.55
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.55.pdf