用大模型自动构建知识图谱，效率远超人工标注。
Construction of Knowledge Graph based on Language Model
- 利用预训练语言模型自动提取文本中的实体与关系
- 轻量级大模型在框架下性能媲美GPT3.5
- 适合需要高效构建知识图谱的工业场景
知识图谱（KG）能有效整合海量数据中的有价值信息，已在多个领域快速发展的广泛应用。传统KG构建依赖人工标注，耗时耗力；而基于深度学习的方法泛化能力较弱。随着预训练语言模型（PLM）的快速发展，其在知识图谱构建领域展现出巨大潜力。本文综述了近年来基于PLM的KG构建研究进展，阐述了如何利用PLM的语言理解与生成能力，从文本中自动提取实体与关系等关键信息。此外，本文提出一种基于轻量级大语言模型（LLM）的新型超关系知识图谱构建框架——LLHKG，并与先前方法进行对比。实验表明，在该框架下，轻量级LLM的KG构建能力可达到GPT3.5水平。
原文摘要 · Abstract (English)
Knowledge Graph (KG) can effectively integrate valuable information from massive data, and thus has been rapidly developed and widely used in many fields. Traditional KG construction methods rely on manual annotation, which often consumes a lot of time and manpower. And KG construction schemes based on deep learning tend to have weak generalization capabilities. With the rapid development of Pre-trained Language Models (PLM), PLM has shown great potential in the field of KG construction. This paper provides a comprehensive review of recent research advances in the field of construction of KGs using PLM. In this paper, we explain how PLM can utilize its language understanding and generation capabilities to automatically extract key information for KGs, such as entities and relations, from textual data. In addition, We also propose a new Hyper-Relarional Knowledge Graph construction framework based on lightweight Large Language Model (LLM) named LLHKG and compares it with previous methods. Under our framework, the KG construction capability of lightweight LLM is comparable to GPT3.5.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。