.png){kind=icon}
返回
Document-level Relation Extraction with Relation Correlations
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2023.11.062.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Document-level relation extraction faces two often overlooked challenges: long-tail problem and multi-label problem. Previous work focuses mainly on obtaining better contextual representations for entity pairs, hardly address the above challenges. In this paper, we analyze the co-occurrence correlation of relations, and introduce it into the document-level relation extraction task for the first time. We argue that the correlations can not only transfer knowledge between data-rich relations and data-scarce ones to assist in the training of long-tailed relations, but also reflect semantic distance guiding the classifier to identify semantically close relations for multi-label entity pairs. Specifically, we use relation embedding as a medium, and propose two co-occurrence prediction sub-tasks from both coarse-and fine-grained perspectives to capture relation correlations. Finally, the learned correlation-aware embeddings are used to guide the extraction of relational facts. Substantial experiments on two popular datasets (i.e., DocRED and DWIE) are conducted, and our method achieves superior results compared to baselines. Insightful analysis also demonstrates the potential of relation correlations to address the above challenges. The data and code are released at https://github.com/RidongHan/DocRE-CoOccur.
Keyword:
Relation Extraction
Relation Correlations
Co-occurrence
Document-level
Multi-task
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.0W
机构
引用论文
分享收藏Distantly Supervised Relation Extraction using Global Hierarchy Embeddings and Local Probability Constraints使用全局层次嵌入和局部概率约束的远距离监督关系提取
PREAI
分享收藏
Synthesis, biologic and toxic effects of the major 2,3,7,8-tetrachlorodibenzo-p-dioxin metabolites in the rat.png)
Toxicology
ToxicologyIF0
PREAI
分享收藏
查看更多内容