Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, Jiawei Han
Abstract
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest challenge of distantly-supervised NER is that the distant supervision may induce incomplete and noisy labels, rendering the straightforward application of supervised learning ineffective. In this paper, we propose (1) a noise-robust learning scheme comprised of a new loss function and a noisy label removal step, for training NER models on distantly-labeled data, and (2) a self-training method that uses contextualized augmentations created by pre-trained language models to improve the generalization ability of the NER model. On three benchmark datasets, our method achieves superior performance, outperforming existing distantly-supervised NER models by significant margins.- Anthology ID:
- 2021.emnlp-main.810
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10367–10378
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.810
- DOI:
- 10.18653/v1/2021.emnlp-main.810
- Cite (ACL):
- Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, and Jiawei Han. 2021. Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10367–10378, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training (Meng et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2021.emnlp-main.810.pdf
- Code
- yumeng5/roster