arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.04835cs.AI
收藏

论知识图谱的演进:综述与展望

On the Evolution of Knowledge Graphs: A Survey and Perspective

International Digital Economy Academy (IDEA)(国际数字经济 academy);Institute of Computing Technology, Chinese Academy of Sciences(计算技术研究所,中国科学院)

Xuhui Jiang, Chengjin Xu, Yinghan Shen, Xun Sun, Lumingyuan Tang, Saizhuo Wang, Zhongwu Chen, Yuanzhuo Wang, Jian Guo

AI总结:

本文全面综述了静态、动态、时序、事件四类知识图谱的演进及相关知识抽取与推理技术,介绍其实际应用并给出金融分析案例,最后展望了知识工程结合大语言模型等未来方向。

摘要:

知识图谱(KGs)是多样化知识的结构化表示,广泛应用于各类智能场景。本文全面综述了不同类型知识图谱(即静态KGs、动态KGs、时序KGs和事件KGs)的演进历程,以及知识抽取与推理技术。此外,本文介绍了不同类型知识图谱的实际应用,包含一个金融分析领域的案例研究。最后,本文提出了对知识工程未来方向的展望,包括结合知识图谱与大语言模型(LLMs)的潜力,以及知识抽取、推理与表示的演进方向。

英文摘要:

Knowledge graphs (KGs) are structured representations of diversified knowledge. They are widely used in various intelligent applications. In this article, we provide a comprehensive survey on the evolution of various types of knowledge graphs (i.e., static KGs, dynamic KGs, temporal KGs, and event KGs) and techniques for knowledge extraction and reasoning. Furthermore, we introduce the practical applications of different types of KGs, including a case study in financial analysis. Finally, we propose our perspective on the future directions of knowledge engineering, including the potential of combining the power of knowledge graphs and large language models (LLMs), and the evolution of knowledge extraction, reasoning, and representation.

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。

↑