CDER: Collaborative Evidence Retrieval for Document-level Relation Extraction
This work addresses a specific bottleneck in document-level relation extraction for NLP researchers, offering an incremental improvement over existing methods.
The paper tackles the problem of evidence retrieval for document-level relation extraction by addressing the overlooked collaborative nature among semantically similar entity pairs, proposing CDER, which improves evidence retrieval and enhances overall system performance on a benchmark dataset.
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.