Year: 2025
Type: preprint
Abstract: Mitigating entity bias is a critical challenge in Relation Extraction (RE), where models often rely excessively on entities, resulting in poor generalization. This paper presents a novel approach to address this issue by adapting a Variational Information Bottleneck (VIB) framework. Our method compresses entity-specific information while preserving task-relevant features. It achieves state-of-the-art performance on relation extraction datasets across general, financial, and biomedical domains, in both indomain (original test sets) and out-of-domain (modified test sets with type-constrained entity replacements) settings. Our approach offers a robust, interpretable, and theoretically grounded methodology.
Source: arXiv (Cornell University)
Authors: Mensah, Samuel, Kochkina, Elena, Magomere, Jabez, Sain, Joy Prakash, Kaur, Simerjot, Smiley, Charese
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415068568
Cites:
Cited by:
Related to: