A Variational Approach for Mitigating Entity Bias in Relation Extraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mensah, Samuel, Kochkina, Elena, Magomere, Jabez, Sain, Joy Prakash, Kaur, Simerjot, Smiley, Charese
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915340783452160
author Mensah, Samuel
Kochkina, Elena
Magomere, Jabez
Sain, Joy Prakash
Kaur, Simerjot
Smiley, Charese
author_facet Mensah, Samuel
Kochkina, Elena
Magomere, Jabez
Sain, Joy Prakash
Kaur, Simerjot
Smiley, Charese
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11381
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Variational Approach for Mitigating Entity Bias in Relation Extraction
Mensah, Samuel
Kochkina, Elena
Magomere, Jabez
Sain, Joy Prakash
Kaur, Simerjot
Smiley, Charese
Computation and Language
Artificial Intelligence
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.
title A Variational Approach for Mitigating Entity Bias in Relation Extraction
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.11381