融合实体和上下文信息的篇章关系抽取研究  

Document-level Relation Extraction With Entity and Context Information

作　　者：黄河燕[1,2] 袁长森 冯冲[1,2] HUANG He-Yan;YUAN Chang-Sen;FENG Chong(School of Computer Science and Technology,Beijing Institute of Technology,Beijing 100081;Natural Language Processing Laboratory,Beijing Institute of Technology,Beijing 100081)

机构地区：[1]北京理工大学计算机学院,北京100081 [2]北京理工大学自然语言处理实验室,北京100081

出　　处：《自动化学报》2024年第10期1953-1962,共10页Acta Automatica Sinica

摘　　要：篇章关系抽取旨在识别篇章中实体对之间的关系.相较于传统的句子级别关系抽取,篇章级别关系抽取任务更加贴近实际应用,但是它对实体对的跨句子推理和上下文信息感知等问题提出了新的挑战.本文提出融合实体和上下文信息(Fuse entity and context information,FECI)的篇章关系抽取方法,它包含两个模块,分别是实体信息抽取模块和上下文信息抽取模块.实体信息抽取模块从两个实体中自动地抽取出能够表示实体对关系的特征.上下文信息抽取模块根据实体对的提及位置信息,从篇章中抽取不同的上下文关系特征.本文在三个篇章级别的关系抽取数据集上进行实验,效果得到显著提升.Document-level relation extraction aims to identify the relations among entities from the document.Compared with traditional sentence-level relation extraction,document-level relation extraction is more realistic and poses new challenges of cross-sentence inference and context information understanding.In this paper,we propose a novel method for document-level relation extraction by fusing entity and context information(FECI),which con-tains two modules:Entity information extraction module and context information extraction module.Entity inform-ation extraction module automatically extracts crucial relation features about entity pair.Context information ex-traction module extracts different context relation features from the document according to mentions'position in-formation of entity pair.We have conducted experiments on three document-level relation extraction datasets,and the effect has been significantly improved.

关 键 词：篇章关系抽取 实体信息 上下文信息 提及位置信息 跨句子推理 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]