Document-level Relation Extraction via Separate Relation Representation and Logical Reasoning
ACM Transactions on Information Systems · 31.01.2024 · 42 (1) · 1-24
DOI: 10.1145/3597610 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 21.08.2023. Verfasst von Heyan Huang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Singapore Ministry of Education (MOE) Academic Research Fund (AcRF) Tier 1 grant, Beijing Institute of Technology Southeast Academy of Information Technology.
Abstract (Originalsprache)
Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this article, we propose a novel model, SRLR , using S eparate Relation R epresentation and L ogical R easoning considering the indirect relation representation and complex reasoning of evidence sentence problems. Specifically, we first expand the judgment of relational facts from the entity-level to the mention-level, highlighting fine-grained information to capture the relation representation for the entity pair. Second, we propose a logical reasoning module to identify evidence sentences and conduct relational reasoning. Extensive experiments on two publicly available benchmark datasets demonstrate the effectiveness of our proposed SRLR as compared to 19 baseline models. Further ablation study also verifies the effects of the key components.
Förderung
- National Natural Science Foundation of China
- Singapore Ministry of Education (MOE) Academic Research Fund (AcRF) Tier 1 grant
- Beijing Institute of Technology Southeast Academy of Information Technology
Zitieren
APA
Huang, H., Yuan, C., Liu, Q., & Cao, Y. (2024). Document-level Relation Extraction via Separate Relation Representation and Logical Reasoning. ACM Transactions on Information Systems, 42(1), 1-24. https://doi.org/10.1145/3597610
Vancouver
Huang H, Yuan C, Liu Q, Cao Y. Document-level Relation Extraction via Separate Relation Representation and Logical Reasoning. ACM Transactions on Information Systems. 2024;42(1):1-24. doi:10.1145/3597610
BibTeX
@article{Huang2024,
author = {Huang, Heyan and Yuan, Changsen and Liu, Qian and Cao, Yixin},
title = {Document-level Relation Extraction via Separate Relation Representation and Logical Reasoning},
journal = {ACM Transactions on Information Systems},
year = {2024},
volume = {42},
number = {1},
pages = {1--24},
doi = {10.1145/3597610}
}
EUVIMED