Abstract
Distant supervision reduces the reliance on human annotation in the named entity recognition tasks. The class-level imbalanced distant annotation is a realistic and unexplored problem, and the popular method of self-training can not handle class-level imbalanced learning. More importantly, self-training is dominated by the high-performance class in selecting candidates, and deteriorates the low-performance class with the bias of generated pseudo label. To address the class-level imbalance performance, we propose a class-rebalancing self-training framework for improving the distantly-supervised named entity recognition. In candidate selection, a class-wise flexible threshold is designed to fully explore other classes besides the high-performance class. In label generation, injecting the distant label, a hybrid pseudo label is adopted to provide straight semantic information for the low-performance class. Experiments on five flat and two nested datasets show that our model achieves state-of-the-art results. We also conduct extensive research to analyze the effectiveness of the flexible threshold and the hybrid pseudo label.- Anthology ID:
- 2023.findings-acl.703
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11054–11068
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.703
- DOI:
- 10.18653/v1/2023.findings-acl.703
- Cite (ACL):
- Qi Li, Tingyu Xie, Peng Peng, Hongwei Wang, and Gaoang Wang. 2023. A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entity Recognition. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11054–11068, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entity Recognition (Li et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.findings-acl.703.pdf