IPED: An Implicit Perspective for Relational Triple Extraction based on Diffusion Model

Jianli Zhao, Changhao Xu, Bin. Jiang

Abstract
Relational triple extraction is a fundamental task in the field of information extraction, and a promising framework based on table filling has recently gained attention as a potential baseline for entity relation extraction. However, inherent shortcomings such as redundant information and incomplete triple recognition remain problematic. To address these challenges, we propose an Implicit Perspective for relational triple Extraction based on Diffusion model (IPED), an innovative approach for extracting relational triples. Our classifier-free solution adopts an implicit strategy using block coverage to complete the tables, avoiding the limitations of explicit tagging methods. Additionally, we introduce a generative model structure, the block-denoising diffusion model, to collaborate with our implicit perspective and effectively circumvent redundant information disruptions. Experimental results on two popular datasets demonstrate that IPED achieves state-of-the-art performance while gaining superior inference speed and low computational complexity. To support future research, we have made our source code publicly available online.
Anthology ID:
2024.naacl-long.114
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2080–2092
Language:
URL:
https://aclanthology.org/2024.naacl-long.114
DOI:
10.18653/v1/2024.naacl-long.114
Bibkey:
Cite (ACL):
Jianli Zhao, Changhao Xu, and Bin. Jiang. 2024. IPED: An Implicit Perspective for Relational Triple Extraction based on Diffusion Model. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2080–2092, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
IPED: An Implicit Perspective for Relational Triple Extraction based on Diffusion Model (Zhao et al., NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.naacl-long.114.pdf
PDF Search