Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field

Zixia Jia, Zhaohui Yan, Wenjuan Han, Zilong Zheng, Kewei Tu


Abstract
Prior works on joint Information Extraction (IE) typically model instance (e.g., event triggers, entities, roles, relations) interactions by representation enhancement, type dependencies scoring, or global decoding. We find that the previous models generally consider binary type dependency scoring of a pair of instances, and leverage local search such as beam search to approximate global solutions. To better integrate cross-instance interactions, in this work, we introduce a joint IE framework (CRFIE) that formulates joint IE as a high-order Conditional Random Field. Specifically, we design binary factors and ternary factors to directly model interactions between not only a pair of instances but also triplets. Then, these factors are utilized to jointly predict labels of all instances. To address the intractability problem of exact high-order inference, we incorporate a high-order neural decoder that is unfolded from a mean-field variational inference method, which achieves consistent learning and inference. The experimental results show that our approach achieves consistent improvements on three IE tasks compared with our baseline and prior work.
Anthology ID:
2023.acl-long.766
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13695–13710
Language:
URL:
https://aclanthology.org/2023.acl-long.766
DOI:
10.18653/v1/2023.acl-long.766
Bibkey:
Cite (ACL):
Zixia Jia, Zhaohui Yan, Wenjuan Han, Zilong Zheng, and Kewei Tu. 2023. Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13695–13710, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field (Jia et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.766.pdf