arXiv 2501.005712025-08-04cs.CL

KnowRA：具有全面推理能力的文档级关系抽取知识检索增强方法

KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities

Nanjing Normal University, School of Computer Science and Electronic Informatics（南京师范大学计算机科学与电子信息学院）；State Key Laboratory for Novel Software Technology at Nanjing University（南京大学新型软件技术国家重点实验室）；Nanjing University, School of Computer Science（南京大学计算机科学学院）

Chengcheng Mai, Yuxiang Wang, Ziyu Gong, Hanxiang Wang, Yihua Huang

备注：: This work has been accepted by IJCAI 2025 (CCF A)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

KnowRA通过构建文档图、检索外部知识并过滤、以及轴注意力机制，实现文档级关系抽取的全面推理，在两个数据集上验证了有效性。

摘要：

文档级关系抽取（Doc-RE）旨在抽取跨多个句子的实体间关系。因此，与句子级关系抽取相比，Doc-RE需要更全面的推理能力，类似于人类，涉及实体、上下文和外部常识知识之间复杂的跨句交互。然而，大多数现有的Doc-RE方法专注于优化单一推理能力，但缺乏利用外部知识对长文档进行全面推理的能力。为解决这些问题，我们提出了一种名为KnowRA的知识检索增强方法，具有全面推理能力，可自主决定是否接受外部知识以辅助Doc-RE。首先，我们构建了用于语义编码的文档图，并集成了共指消解模型以增强共指推理能力。然后，我们通过检索外部知识库将文档图扩展为文档知识图，以进行常识推理，并提出了一种新颖的知识过滤方法来过滤不相关的知识。最后，我们提出了轴注意力机制，以通过中间实体建立直接和间接关联，实现跨句逻辑推理。在两个数据集上进行的大量实验验证了我们的方法相对于最先进基线的有效性。我们的代码可在https://anonymous.4open.science/r/KnowRA获取。

英文摘要：

Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions between entities, contexts, and external general knowledge, compared to the sentence-level RE. However, most existing Doc-RE methods focus on optimizing single reasoning ability, but lack the ability to utilize external knowledge for comprehensive reasoning on long documents. To solve these problems, a knowledge retrieval augmented method, named KnowRA, was proposed with comprehensive reasoning to autonomously determine whether to accept external knowledge to assist DocRE. Firstly, we constructed a document graph for semantic encoding and integrated the co-reference resolution model to augment the co-reference reasoning ability. Then, we expanded the document graph into a document knowledge graph by retrieving the external knowledge base for common-sense reasoning and a novel knowledge filtration method was presented to filter out irrelevant knowledge. Finally, we proposed the axis attention mechanism to build direct and indirect associations with intermediary entities for achieving cross-sentence logical reasoning. Extensive experiments conducted on two datasets verified the effectiveness of our method compared to the state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/KnowRA.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。