Adaptive Ordered Information Extraction with Deep Reinforcement Learning

Wenhao Huang, Jiaqing Liang, Zhixu Li, Yanghua Xiao, Chuanjun Ji


Abstract
Information extraction (IE) has been studied extensively. The existing methods always follow a fixed extraction order for complex IE tasks with multiple elements to be extracted in one instance such as event extraction. However, we conduct experiments on several complex IE datasets and observe that different extraction orders can significantly affect the extraction results for a great portion of instances, and the ratio of sentences that are sensitive to extraction orders increases dramatically with the complexity of the IE task. Therefore, this paper proposes a novel adaptive ordered IE paradigm to find the optimal element extraction order for different instances, so as to achieve the best extraction results. We also propose an reinforcement learning (RL) based framework to generate optimal extraction order for each instance dynamically. Additionally, we propose a co-training framework adapted to RL to mitigate the exposure bias during the extractor training phase. Extensive experiments conducted on several public datasets demonstrate that our proposed method can beat previous methods and effectively improve the performance of various IE tasks, especially for complex ones.
Anthology ID:
2023.findings-acl.863
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13664–13678
Language:
URL:
https://aclanthology.org/2023.findings-acl.863
DOI:
10.18653/v1/2023.findings-acl.863
Bibkey:
Cite (ACL):
Wenhao Huang, Jiaqing Liang, Zhixu Li, Yanghua Xiao, and Chuanjun Ji. 2023. Adaptive Ordered Information Extraction with Deep Reinforcement Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13664–13678, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Adaptive Ordered Information Extraction with Deep Reinforcement Learning (Huang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.863.pdf
Video:
 https://aclanthology.org/2023.findings-acl.863.mp4