Saved in:
Bibliographic Details
Main Authors: He, Liang, Chu, Yougang, Wu, Zhen, Zhang, Jianbing, Dai, Xinyu, Chen, Jiajun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.01349
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913633545486336
author He, Liang
Chu, Yougang
Wu, Zhen
Zhang, Jianbing
Dai, Xinyu
Chen, Jiajun
author_facet He, Liang
Chu, Yougang
Wu, Zhen
Zhang, Jianbing
Dai, Xinyu
Chen, Jiajun
contents Benchmarks are crucial for evaluating machine learning algorithm performance, facilitating comparison and identifying superior solutions. However, biases within datasets can lead models to learn shortcut patterns, resulting in inaccurate assessments and hindering real-world applicability. This paper addresses the issue of entity bias in relation extraction tasks, where models tend to rely on entity mentions rather than context. We propose a debiased relation extraction benchmark DREB that breaks the pseudo-correlation between entity mentions and relation types through entity replacement. DREB utilizes Bias Evaluator and PPL Evaluator to ensure low bias and high naturalness, providing a reliable and accurate assessment of model generalization in entity bias scenarios. To establish a new baseline on DREB, we introduce MixDebias, a debiasing method combining data-level and model training-level techniques. MixDebias effectively improves model performance on DREB while maintaining performance on the original dataset. Extensive experiments demonstrate the effectiveness and robustness of MixDebias compared to existing methods, highlighting its potential for improving the generalization ability of relation extraction models. We will release DREB and MixDebias publicly.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01349
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark
He, Liang
Chu, Yougang
Wu, Zhen
Zhang, Jianbing
Dai, Xinyu
Chen, Jiajun
Artificial Intelligence
Benchmarks are crucial for evaluating machine learning algorithm performance, facilitating comparison and identifying superior solutions. However, biases within datasets can lead models to learn shortcut patterns, resulting in inaccurate assessments and hindering real-world applicability. This paper addresses the issue of entity bias in relation extraction tasks, where models tend to rely on entity mentions rather than context. We propose a debiased relation extraction benchmark DREB that breaks the pseudo-correlation between entity mentions and relation types through entity replacement. DREB utilizes Bias Evaluator and PPL Evaluator to ensure low bias and high naturalness, providing a reliable and accurate assessment of model generalization in entity bias scenarios. To establish a new baseline on DREB, we introduce MixDebias, a debiasing method combining data-level and model training-level techniques. MixDebias effectively improves model performance on DREB while maintaining performance on the original dataset. Extensive experiments demonstrate the effectiveness and robustness of MixDebias compared to existing methods, highlighting its potential for improving the generalization ability of relation extraction models. We will release DREB and MixDebias publicly.
title Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark
topic Artificial Intelligence
url https://arxiv.org/abs/2501.01349