Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction

Zehan Li, Fu Zhang, Kailun Lyu, Jingwei Cheng, Tianyue Peng


Abstract
Zero-shot Relation Triplet Extraction (ZSRTE) aims to extract triplets from the context where the relation patterns are unseen during training. Due to the inherent challenges of the ZSRTE task, existing extractive ZSRTE methods often decompose it into named entity recognition and relation classification, which overlooks the interdependence of two tasks and may introduce error propagation. Motivated by the intuition that crucial entity attributes might be implicit in the relation labels, we propose a Relation-Centric joint ZSRTE method named Re-Cent. This approach uses minimal information, specifically unseen relation labels, to extract triplets in one go through a unified model. We develop two span-based extractors to identify the subjects and objects corresponding to relation labels, forming span-pairs. Additionally, we introduce a relation-based correction mechanism that further refines the triplets by calculating the relevance between span-pairs and relation labels. Experiments demonstrate that Re-Cent achieves state-of-the-art performance with fewer parameters and does not rely on synthetic data or manual labor.
Anthology ID:
2025.coling-main.491
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7344–7354
Language:
URL:
https://aclanthology.org/2025.coling-main.491/
DOI:
Bibkey:
Cite (ACL):
Zehan Li, Fu Zhang, Kailun Lyu, Jingwei Cheng, and Tianyue Peng. 2025. Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7344–7354, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction (Li et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.491.pdf