Abstract
Relation extraction (RE) has recently moved from the sentence-level to document-level, which requires aggregating document information and using entities and mentions for reasoning. Existing works put entity nodes and mention nodes with similar representations in a document-level graph, whose complex edges may incur redundant information. Furthermore, existing studies only focus on entity-level reasoning paths without considering global interactions among entities cross-sentence. To these ends, we propose a novel document-level RE model with a GRaph information Aggregation and Cross-sentence Reasoning network (GRACR). Specifically, a simplified document-level graph is constructed to model the semantic information of all mentions and sentences in a document, and an entity-level graph is designed to explore relations of long-distance cross-sentence entity pairs. Experimental results show that GRACR achieves excellent performance on two public datasets of document-level RE. It is especially effective in extracting potential relations of cross-sentence entity pairs. Our code is available at this https URL.
Abstract (translated)
关系提取(RE)最近从句子级别转移到文档级别,这需要将文档信息聚合并使用实体和提及进行推理。现有工作将实体节点和提及节点以类似的表现方式放在文档级别的图中,其复杂的边可能包含冗余信息。此外,现有研究仅关注实体级别的推理路径,未考虑跨句子实体之间的全球交互。为此,我们提出了一种新的文档级别的RE模型,结合GRaph信息聚合和跨句子推理网络(GRACR)。具体而言,我们创造了一种简化的文档级别的图来建模文档中所有提及和句子的语义信息,并设计了实体级别的图来探索长距离跨句子实体 pairs 的关系。实验结果表明,GRACR在两个文档级别的RE公共数据集上表现优异。它在提取跨句子实体 pairs 的潜在关系方面特别有效。我们的代码在这个httpsURL上可用。
URL
https://arxiv.org/abs/2303.03912