In the recent digitization era, capturing, representing, and understanding knowledge is essential in countless real-world scenarios. Knowledge graphs emerged as a powerful tool for representing information through an adequately interconnected and interpretable structure in such a context. Nevertheless, generating proper knowledge graphs usually requires significant manual effort and domain expertise, resulting in graphs often affected by human subjectivity, limited scalability, or inability to capture implicit knowledge or handle heterogeneity. This paper proposes an innovative zero-shot strategy tailored to uncover reliable knowledge from text leveraging the recent highly effective generative large language models, with a particular focus on the GPT-3.5 model. Our proposal aims to create a suitable knowledge graph or improve existing ones by discovering missing qualitative triples. To assess the effectiveness of our methodology, we performed experiments on domain-specific datasets, confirming its potential for scalable and versatile knowledge discovery.

A Zero-Shot Strategy for Knowledge Graph Engineering Using GPT-3.5

Carta, Salvatore;Giuliani, Alessandro;Manca, Marco Manolo;Piano, Leonardo;Podda, Alessandro Sebastian;Pompianu, Livio;Tiddia, Sandro Gabriele
2024-01-01

Abstract

In the recent digitization era, capturing, representing, and understanding knowledge is essential in countless real-world scenarios. Knowledge graphs emerged as a powerful tool for representing information through an adequately interconnected and interpretable structure in such a context. Nevertheless, generating proper knowledge graphs usually requires significant manual effort and domain expertise, resulting in graphs often affected by human subjectivity, limited scalability, or inability to capture implicit knowledge or handle heterogeneity. This paper proposes an innovative zero-shot strategy tailored to uncover reliable knowledge from text leveraging the recent highly effective generative large language models, with a particular focus on the GPT-3.5 model. Our proposal aims to create a suitable knowledge graph or improve existing ones by discovering missing qualitative triples. To assess the effectiveness of our methodology, we performed experiments on domain-specific datasets, confirming its potential for scalable and versatile knowledge discovery.
2024
Knowledge Engineering; Knowledge Graphs; Large Language Models
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S1877050924026231-main.pdf

accesso aperto

Tipologia: versione editoriale (VoR)
Dimensione 997.8 kB
Formato Adobe PDF
997.8 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/433806
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact