用生成模型增强文档关系抽取中的少数类别数据
VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction
- 基于变分自编码器和扩散模型，从嵌入空间生成少样本关系数据
- 在两个基准数据集上显著提升长尾关系的抽取效果
- 适合处理标注不均衡的真实文档关系抽取任务
文档级关系抽取（DocRE）旨在识别文档中实体对之间的关系。然而，现有方法多假设标签分布均匀，导致在真实世界中存在标签不平衡的数据集上表现不佳。为此，我们提出一种基于生成模型的数据增强方法，通过变分自编码器（VAE）捕捉实体对表示形成的关系分布，并对低频关系进行数据扩充。为更好建模DocRE的多标签特性，我们使用扩散模型参数化VAE的隐空间。此外，设计了分层训练框架，将提出的VAE增强模块集成到DocRE系统中。在两个基准数据集上的实验表明，该方法优于当前最先进模型，有效缓解了DocRE中的长尾分布问题。
原文摘要 · Abstract (English)
Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets. To tackle this challenge, we propose a novel data augmentation approach using generative models to enhance data from the embedding space. Our method leverages the Variational Autoencoder (VAE) architecture to capture all relation-wise distributions formed by entity pair representations and augment data for underrepresented relations. To better capture the multi-label nature of DocRE, we parameterize the VAE's latent space with a Diffusion Model. Additionally, we introduce a hierarchical training framework to integrate the proposed VAE-based augmentation module into DocRE systems. Experiments on two benchmark datasets demonstrate that our method outperforms state-of-the-art models, effectively addressing the long-tail distribution problem in DocRE.
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。