Key Mention Pairs Guided Document-Level Relation Extraction

Feng Jiang, Jianwei Niu, Shasha Mo, Shengda Fan


Abstract
Document-level Relation Extraction (DocRE) aims at extracting relations between entities in a given document. Since different mention pairs may express different relations or even no relation, it is crucial to identify key mention pairs responsible for the entity-level relation labels. However, most recent studies treat different mentions equally while predicting the relations between entities, leading to sub-optimal performance. To this end, we propose a novel DocRE model called Key Mention pairs Guided Relation Extractor (KMGRE) to directly model mention-level relations, containing two modules: a mention-level relation extractor and a key instance classifier. These two modules could be iteratively optimized with an EM-based algorithm to enhance each other. We also propose a new method to solve the multi-label problem in optimizing the mention-level relation extractor. Experimental results on two public DocRE datasets demonstrate that the proposed model is effective and outperforms previous state-of-the-art models.
Anthology ID:
2022.coling-1.165
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1904–1914
Language:
URL:
https://aclanthology.org/2022.coling-1.165
DOI:
Bibkey:
Cite (ACL):
Feng Jiang, Jianwei Niu, Shasha Mo, and Shengda Fan. 2022. Key Mention Pairs Guided Document-Level Relation Extraction. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1904–1914, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Key Mention Pairs Guided Document-Level Relation Extraction (Jiang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.165.pdf
Data
DWIEDocRED