%0 Conference Proceedings %T Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation %A Yoon, Sangwon %A Kim, Yanghoon %A Jung, Kyomin %Y Palmer, Alexis %Y Schneider, Nathan %Y Schluter, Natalie %Y Emerson, Guy %Y Herbelot, Aurelie %Y Zhu, Xiaodan %S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021) %D 2021 %8 August %I Association for Computational Linguistics %C Online %F yoon-etal-2021-self %X 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. %R 10.18653/v1/2021.semeval-1.55 %U https://aclanthology.org/2021.semeval-1.55 %U https://doi.org/10.18653/v1/2021.semeval-1.55 %P 452-457