Effective Modeling of Generative Framework for Document-level Relational Triple Extraction

Pratik Saini, Tapas Nayak


Abstract
Document-level relation triple extraction (DocRTE) is a complex task that involves three key sub-tasks: entity mention extraction, entity clustering, and relation triple extraction. Past work has applied discriminative models to address these three sub-tasks, either by training them sequentially in a pipeline fashion or jointly training them. However, while end-to-end discriminative or generative models have proven effective for sentence-level relation triple extraction, they cannot be trivially extended to the document level, as they only handle relation extraction without addressing the remaining two sub-tasks, entity mention extraction or clustering. In this paper, we propose a three-stage generative framework leveraging a pre-trained BART model to address all three tasks required for document-level relation triple extraction. Tested on the widely used DocRED dataset, our approach outperforms previous generative methods and achieves competitive performance against discriminative models.
Anthology ID:
2025.genaik-1.1
Volume:
Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Genet Asefa Gesese, Harald Sack, Heiko Paulheim, Albert Merono-Penuela, Lihu Chen
Venues:
GenAIK | WS
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1–12
Language:
URL:
https://aclanthology.org/2025.genaik-1.1/
DOI:
Bibkey:
Cite (ACL):
Pratik Saini and Tapas Nayak. 2025. Effective Modeling of Generative Framework for Document-level Relational Triple Extraction. In Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK), pages 1–12, Abu Dhabi, UAE. International Committee on Computational Linguistics.
Cite (Informal):
Effective Modeling of Generative Framework for Document-level Relational Triple Extraction (Saini & Nayak, GenAIK 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.genaik-1.1.pdf