Abstract
This paper describes PTST, a source-free unsupervised domain adaptation technique for sequence tagging, and its application to the SemEval-2021 Task 10 on time expression recognition. PTST is an extension of the cross-lingual parsimonious parser transfer framework, which uses high-probability predictions of the source model as a supervision signal in self-training. We extend the framework to a sequence prediction setting, and demonstrate its applicability to unsupervised domain adaptation. PTST achieves F1 score of 79.6% on the official test set, with the precision of 90.1%, the highest out of 14 submissions.- Anthology ID:
- 2021.semeval-1.54
- 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:
- 445–451
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2021.semeval-1.54/
- DOI:
- 10.18653/v1/2021.semeval-1.54
- Cite (ACL):
- Kemal Kurniawan, Lea Frermann, Philip Schulz, and Trevor Cohn. 2021. PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 445–451, Online. Association for Computational Linguistics.
- Cite (Informal):
- PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging (Kurniawan et al., SemEval 2021)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2021.semeval-1.54.pdf