Denoising Relation Extraction from Document-level Distant Supervision

Chaojun Xiao, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Maosong Sun, Fen Lin, Leyu Lin


Abstract
Distant supervision (DS) has been widely adopted to generate auto-labeled data for sentence-level relation extraction (RE) and achieved great results. However, the existing success of DS cannot be directly transferred to more challenging document-level relation extraction (DocRE), as the inevitable noise caused by DS may be even multiplied in documents and significantly harm the performance of RE. To alleviate this issue, we propose a novel pre-trained model for DocRE, which de-emphasize noisy DS data via multiple pre-training tasks. The experimental results on the large-scale DocRE benchmark show that our model can capture useful information from noisy data and achieve promising results.
Anthology ID:
2020.emnlp-main.300
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3683–3688
Language:
URL:
https://aclanthology.org/2020.emnlp-main.300
DOI:
10.18653/v1/2020.emnlp-main.300
Bibkey:
Cite (ACL):
Chaojun Xiao, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Maosong Sun, Fen Lin, and Leyu Lin. 2020. Denoising Relation Extraction from Document-level Distant Supervision. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3683–3688, Online. Association for Computational Linguistics.
Cite (Informal):
Denoising Relation Extraction from Document-level Distant Supervision (Xiao et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.300.pdf
Video:
 https://slideslive.com/38938935
Code
 thunlp/DSDocRE
Data
DocRED