Learning Cross-Task Dependencies for Joint Extraction of Entities, Events, Event Arguments, and Relations

Minh Van Nguyen, Bonan Min, Franck Dernoncourt, Thien Nguyen


Abstract
Extracting entities, events, event arguments, and relations (i.e., task instances) from text represents four main challenging tasks in information extraction (IE), which have been solved jointly (JointIE) to boost the overall performance for IE. As such, previous work often leverages two types of dependencies between the tasks, i.e., cross-instance and cross-type dependencies representing relatedness between task instances and correlations between information types of the tasks. However, the cross-task dependencies in prior work are not optimal as they are only designed manually according to some task heuristics. To address this issue, we propose a novel model for JointIE that aims to learn cross-task dependencies from data. In particular, we treat each task instance as a node in a dependency graph where edges between the instances are inferred through information from different layers of a pretrained language model (e.g., BERT). Furthermore, we utilize the Chow-Liu algorithm to learn a dependency tree between information types for JointIE by seeking to approximate the joint distribution of the types from data. Finally, the Chow-Liu dependency tree is used to generate cross-type patterns, serving as anchor knowledge to guide the learning of representations and dependencies between instances for JointIE. Experimental results show that our proposed model significantly outperforms strong JointIE baselines over four datasets with different languages.
Anthology ID:
2022.emnlp-main.634
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9349–9360
Language:
URL:
https://aclanthology.org/2022.emnlp-main.634
DOI:
10.18653/v1/2022.emnlp-main.634
Bibkey:
Cite (ACL):
Minh Van Nguyen, Bonan Min, Franck Dernoncourt, and Thien Nguyen. 2022. Learning Cross-Task Dependencies for Joint Extraction of Entities, Events, Event Arguments, and Relations. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9349–9360, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Learning Cross-Task Dependencies for Joint Extraction of Entities, Events, Event Arguments, and Relations (Nguyen et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.634.pdf