基于远程监督的关系抽取研究综述

Overview of distant supervision based relation extraction

远程监督为关系抽取任务自动构建数据集,可解决从海量数据信息中无法被快速且准确抽取实体间关系这一问题,缓解构建数据集时的人工和经济成本压力,因此远程监督是近些年自然语言处理技术研究的热点。本文介绍了远程监督关系抽取的研究思路和现状,分析了存在的问题及解决方法,总结了远程监督关系抽取的主要应用领域,提出了该领域研究重点难点以及未来可能发展的方向,以期为相关研究提供参考。

To solve the problem that relationships between entities cannot be extracted quickly and accurately from massive data,remote supervision automatically constructs datasets for relation extraction task,which alleviates the pressure of labor and economic costs in the construction of datasets.Remote supervision has become a hot topic in the research of natural language processing technology in recent years.In this paper,the main research problems and solutions of remote supervised relationship extraction are sorted out,the main application fields of remote supervised relationship extraction are summarized,and the future development direction and challenges of remote supervised relationship extraction are analyzed.It provides guidance for researchers in this field.