SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework

Fu Zhang, Qi Miao, Jingwei Cheng, Hongsen Yu, Yi Yan, Xin Li, Yongxue Wu


Abstract
Document-level Relation Extraction (DocRE) aims to extract relations between entity pairs in a document and poses many challenges as it involves multiple mentions of entities and cross-sentence inference. However, several aspects that are important for DocRE have not been considered and explored. Existing work ignores bidirectional mention interaction when generating relational features for entity pairs. Also, sophisticated neural networks are typically designed for cross-sentence evidence extraction to further enhance DocRE. More interestingly, we reveal a noteworthy finding: If a model has predicted a relation between an entity and other entities, this relation information may help infer and predict more relations between the entity’s adjacent entities and these other entities. Nonetheless, none of existing methods leverage secondary reasoning to exploit results of relation prediction. To this end, we propose a novel Secondary Reasoning Framework (SRF) for DocRE. In SRF, we initially propose a DocRE model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module (incurring only an additional learnable parameter overhead) for relation prediction. Further, for the first time, we elaborately design and propose a novel secondary reasoning method to discover more relations by exploring the results of the first relation prediction. Extensive experiments show that SRF achieves SOTA performance and our secondary reasoning method is both effective and general when integrated into existing models.
Anthology ID:
2024.emnlp-main.863
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15426–15439
Language:
URL:
https://aclanthology.org/2024.emnlp-main.863
DOI:
Bibkey:
Cite (ACL):
Fu Zhang, Qi Miao, Jingwei Cheng, Hongsen Yu, Yi Yan, Xin Li, and Yongxue Wu. 2024. SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15426–15439, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework (Zhang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.863.pdf