Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2504.06529 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912317405396992 |
|---|---|
| author | Tran, Khai Phan Li, Xue |
| author_facet | Tran, Khai Phan Li, Xue |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06529 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CDER: Collaborative Evidence Retrieval for Document-level Relation Extraction Tran, Khai Phan Li, Xue Computation and Language 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. |
| title | CDER: Collaborative Evidence Retrieval for Document-level Relation Extraction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.06529 |