Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents

Daoyuan Chen, Yaliang Li, Kai Lei, Ying Shen


Abstract
Distant supervision based methods for entity and relation extraction have received increasing popularity due to the fact that these methods require light human annotation efforts. In this paper, we consider the problem of shifted label distribution, which is caused by the inconsistency between the noisy-labeled training set subject to external knowledge graph and the human-annotated test set, and exacerbated by the pipelined entity-then-relation extraction manner with noise propagation. We propose a joint extraction approach to address this problem by re-labeling noisy instances with a group of cooperative multiagents. To handle noisy instances in a fine-grained manner, each agent in the cooperative group evaluates the instance by calculating a continuous confidence score from its own perspective; To leverage the correlations between these two extraction tasks, a confidence consensus module is designed to gather the wisdom of all agents and re-distribute the noisy training set with confidence-scored labels. Further, the confidences are used to adjust the training losses of extractors. Experimental results on two real-world datasets verify the benefits of re-labeling noisy instance, and show that the proposed model significantly outperforms the state-of-the-art entity and relation extraction methods.
Anthology ID:
2020.acl-main.527
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5940–5950
Language:
URL:
https://aclanthology.org/2020.acl-main.527
DOI:
10.18653/v1/2020.acl-main.527
Bibkey:
Cite (ACL):
Daoyuan Chen, Yaliang Li, Kai Lei, and Ying Shen. 2020. Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5940–5950, Online. Association for Computational Linguistics.
Cite (Informal):
Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents (Chen et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.527.pdf
Video:
 http://slideslive.com/38928879
Data
FIGER