Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting

Linzhi Wu, Pengjun Xie, Jie Zhou, Meishan Zhang, Ma Chunping, Guangwei Xu, Min Zhang


Abstract
Self-augmentation has received increasing research interest recently to improve named entity recognition (NER) performance in low-resource scenarios. Token substitution and mixup are two feasible heterogeneous self-augmentation techniques for NER that can achieve effective performance with certain specialized efforts. Noticeably, self-augmentation may introduce potentially noisy augmented data. Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually. In this paper, we revisit these two typical self-augmentation methods for NER, and propose a unified meta-reweighting strategy for them to achieve a natural integration. Our method is easily extensible, imposing little effort on a specific self-augmentation method. Experiments on different Chinese and English NER benchmarks show that our token substitution and mixup method, as well as their integration, can achieve effective performance improvement. Based on the meta-reweighting mechanism, we can enhance the advantages of the self-augmentation techniques without much extra effort.
Anthology ID:
2022.naacl-main.297
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4049–4060
Language:
URL:
https://aclanthology.org/2022.naacl-main.297
DOI:
10.18653/v1/2022.naacl-main.297
Bibkey:
Cite (ACL):
Linzhi Wu, Pengjun Xie, Jie Zhou, Meishan Zhang, Ma Chunping, Guangwei Xu, and Min Zhang. 2022. Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4049–4060, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting (Wu et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.297.pdf
Software:
 2022.naacl-main.297.software.zip
Video:
 https://aclanthology.org/2022.naacl-main.297.mp4
Code
 LindgeW/MetaAug4NER
Data
CoNLL 2003OntoNotes 5.0Weibo NER