A Variational Approach for Mitigating Entity Bias in Relation Extraction
Samuel Mensah, Elena Kochkina, Jabez Magomere, Joy Prakash Sain, Simerjot Kaur, Charese Smiley
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 both general and financial domain RE datasets, excelling in in-domain settings (original test sets) and out-of-domain (modified test sets with type-constrained entity replacements). Our approach offers a robust, interpretable, and theoretically grounded methodology.
BibTeX
@inproceedings{mensah-etal-2025-variational,
title = "A Variational Approach for Mitigating Entity Bias in Relation Extraction",
author = "Mensah, Samuel and
Kochkina, Elena and
Magomere, Jabez and
Sain, Joy Prakash and
Kaur, Simerjot and
Smiley, Charese",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-short.53/",
doi = "10.18653/v1/2025.acl-short.53",
pages = "676--684",
ISBN = "979-8-89176-252-7"
}