Construction of Knowledge Graph based on Language Model

TL;DR

This paper reviews recent advances in constructing knowledge graphs using pre-trained language models and introduces a new lightweight LLM-based framework called LLHKG, achieving comparable results to GPT-3.5.

Contribution

It provides a comprehensive review of PLM-based KG construction and proposes the LLHKG framework for efficient, high-quality knowledge graph construction.

Findings

Lightweight LLMs can match GPT-3.5 in KG construction quality.

The paper introduces a Hyper-Relational KG construction framework.

PLMs effectively extract entities and relations from text for KG building.

Abstract

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.