Abstract
Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document. Evidence sentences, crucial for precise entity pair relationships identification, enhance focus on essential text segments, improving DocRE performance. However, existing evidence retrieval systems often overlook the collaborative nature among semantically similar entity pairs in the same document, hindering the effectiveness of the evidence retrieval task. To address this, we propose a novel evidence retrieval framework, namely CDER. CDER employs an attentional graph-based architecture to capture collaborative patterns and incorporates a dynamic sub-structure for additional robustness in evidence retrieval. Experimental results on the benchmark DocRE dataset show that CDER not only excels in the evidence retrieval task but also enhances overall performance of existing DocRE system.
Abstract (translated)
文档级关系抽取（DocRE）涉及在文档的多句话中识别实体之间的关系。证据句子对于精确识别实体对的关系至关重要，它们有助于聚焦于关键文本片段，从而提高文档级关系抽取的效果。然而，现有的证据检索系统常常忽视了同一文档中语义相似的实体对之间相互协作的本质特征，这限制了证据检索任务的有效性。为此，我们提出了一种新的证据检索框架，即CDER（Collaborative Evidence Retrieval）。CDER采用注意力图网络架构来捕捉协作模式，并结合动态子结构以增强证据检索的鲁棒性。在DocRE基准数据集上的实验结果表明，CDER不仅在证据检索任务中表现出色，还提升了现有文档级关系抽取系统的整体性能。
URL
https://arxiv.org/abs/2504.06529
