Boosting Document-Level Relation Extraction by Mining and Injecting Logical Rules

Shengda Fan, Shasha Mo, Jianwei Niu


Abstract
Document-level relation extraction (DocRE) aims at extracting relations of all entity pairs in a document. A key challenge to DocRE lies in the complex interdependency between the relations of entity pairs. Unlike most prior efforts focusing on implicitly powerful representations, the recently proposed LogiRE (Ru et al., 2021) explicitly captures the interdependency by learning logical rules. However, LogiRE requires extra parameterized modules to reason merely after training backbones, and this disjointed optimization of backbones and extra modules may lead to sub-optimal results. In this paper, we propose MILR, a logic enhanced framework that boosts DocRE by Mining and Injecting Logical Rules. MILR first mines logical rules from annotations based on frequencies. Then in training, consistency regularizationis leveraged as an auxiliary loss to penalize instances that violate mined rules. Finally, MILR infers from a global perspective based on integer programming. Compared with LogiRE, MILR does not introduce extra parameters and injects logical rules during both training and inference. Extensive experiments on two benchmarks demonstrate that MILR not only improves the relation extraction performance (1.1%-3.8% F1) but also makes predictions more logically consistent (over 4.5% Logic). More importantly, MILR also consistently outperforms LogiRE on both counts. Code is available at https://github.com/XingYing-stack/MILR.
Anthology ID:
2022.emnlp-main.704
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:
10311–10323
Language:
URL:
https://aclanthology.org/2022.emnlp-main.704
DOI:
10.18653/v1/2022.emnlp-main.704
Bibkey:
Cite (ACL):
Shengda Fan, Shasha Mo, and Jianwei Niu. 2022. Boosting Document-Level Relation Extraction by Mining and Injecting Logical Rules. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10311–10323, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Boosting Document-Level Relation Extraction by Mining and Injecting Logical Rules (Fan et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.704.pdf