Search papers, labs, and topics across Lattice.
This paper reviews the use of Pre-trained Language Models (PLMs) for Knowledge Graph (KG) construction, highlighting their ability to automate entity and relation extraction from text. It addresses the limitations of manual annotation and the weak generalization of deep learning-based KG construction methods. The authors introduce LLHKG, a Hyper-Relational KG construction framework based on a lightweight LLM, demonstrating performance comparable to GPT-3.5.
Lightweight LLMs can achieve Knowledge Graph construction performance rivaling GPT-3.5, suggesting a path to more efficient and accessible KG creation.
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.
