Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning

Xinghua Zhang, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Jiawei Sheng, Xue Mengge, Hongbo Xu


Abstract
Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision. Typically, the wrongly labeled instances comprise numbers of incomplete and inaccurate annotations, while most prior denoising works are only concerned with one kind of noise and fail to fully explore useful information in the training set. To address this issue, we propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student networks in a mutually-beneficial manner to iteratively perform noisy label refinery. Each network is designed to exploit reliable labels via self denoising, and two networks communicate with each other to explore unreliable annotations by collaborative denoising. Extensive experimental results on five real-world datasets demonstrate that SCDL is superior to state-of-the-art DS-NER denoising methods.
Anthology ID:
2021.findings-emnlp.131
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1518–1529
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.131
DOI:
10.18653/v1/2021.findings-emnlp.131
Bibkey:
Cite (ACL):
Xinghua Zhang, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Jiawei Sheng, Xue Mengge, and Hongbo Xu. 2021. Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1518–1529, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning (Zhang et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.131.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.131.mp4