摘要
随着人工智能技术的高速发展,“信息爆炸和知识缺乏”的矛盾愈发凸显。通过知识抽取技术从海量异构数据中自动、快速、准确地抽取人们感兴趣的知识并将其以结构化的知识存储起来,是解决上述矛盾的有效途径之一。系统介绍了面向知识图谱构建的知识抽取技术,分析比较了该领域不同方法之间的优缺点,同时对各个技术的研究进展和使用方法进行了总结,并对知识抽取领域仍需进一步关注的问题提出了思考。
With the rapid development of artificial intelligence technology,the contradiction between“information overload”and“lack of knowledge”has become increasingly prominent.It is one of the effective ways to solve the above-mentioned problems by using knowledge extraction technology to automatically,quickly and accurately extract people’s interested knowledge from massive heterogeneous data and store it as structured knowledge.This paper systematically introduces the knowledge extraction technology for the construction of knowledge graph,analyzes and compares the advantages and disadvantages of different methods in this area,summarizes the research progress and practical methods of each technology,and puts forward some thoughts on the problems that need further attention in the area of knowledge extraction.
作者
于浏洋
郭志刚
陈刚
席耀一
YU Liuyang;GUO Zhigang;CHEN Gang;XI Yaoyi(Information Engineering University,Zhengzhou 450001,China)
出处
《信息工程大学学报》
2020年第2期227-235,共9页
Journal of Information Engineering University
基金
国家社会科学基金资助项目(19CXW027)。
关键词
知识抽取
实体抽取
关系抽取
属性抽取
事件抽取
知识图谱
knowledge extraction
entity extraction
relationship extraction
attribute extraction
event extraction
knowledge graph
作者简介
于浏洋(1991-),女,硕士生,助理工程师,主要研究方向为智能信息处理。
