用变分信息瓶颈压缩实体信息，提升关系抽取泛化能力
A Variational Approach for Mitigating Entity Bias in Relation Extraction
- 引入变分信息瓶颈框架，压缩实体特有信息
- 在跨领域测试中均达当前最优性能
- 方法可解释且理论基础扎实，适合高可靠性场景
关系抽取中的实体偏差问题严重影响模型泛化能力，现有模型过度依赖实体信息。本文提出一种基于变分信息瓶颈（VIB）的新方法，通过压缩实体特异性信息同时保留任务相关特征来缓解该问题。在通用、金融和生物医学三个领域的数据集上，无论是在原始测试集（域内）还是经类型约束实体替换后的测试集（域外）中，该方法均取得当前最佳表现。所提方法具备鲁棒性、可解释性及坚实的理论基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。