Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis

In Ontology-Based Data Access (OBDA), we study how to represent legacy data sources using ontologies. This enables a modern, distributed, uniform data representation format with the ability to perform intelligent querying and processing. This task requires the development of software to interpret th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gómez, Sergio Alejandro, Fillottrani, Pablo Rubén
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2024
Materias:	Ciencias Informáticas Ontology-Based Data Access Large Language Models Ontologies CSV
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/176820
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-176820
record_format	dspace
spelling	I19-R120-10915-1768202025-02-21T20:03:44Z http://sedici.unlp.edu.ar/handle/10915/176820 Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis Gómez, Sergio Alejandro Fillottrani, Pablo Rubén 2024-10 2024 2025-02-21T17:58:03Z en Ciencias Informáticas Ontology-Based Data Access Large Language Models Ontologies CSV In Ontology-Based Data Access (OBDA), we study how to represent legacy data sources using ontologies. This enables a modern, distributed, uniform data representation format with the ability to perform intelligent querying and processing. This task requires the development of software to interpret the data and express it as ontologies, which takes considerable time. On the other hand, large language models (LLM) have lately shown themselves to be great solution providers due to their ability to generate solutions from input specified in natural language by an end user. In this paper, we explore the potential of LLM to perform OBDA automatically. Our research hypothesis is that is possible to use an LLM tool like ChatGPT to perform OBDA. For this purpose, we studied ChatGPT responses with different problems associated with OBDA. We discovered that ChatGPT is able to generate ontologies from free text as well as from tables expressed as text or in CSV format. ChatGPT is also able to generate SPARQL queries, and it is also successful in expressing relational tables as ontologies being capable of correcting violations of integrity constraints when appropriately directed. Red de Universidades con Carreras en Informática Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 996-1005
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Ontology-Based Data Access Large Language Models Ontologies CSV
spellingShingle	Ciencias Informáticas Ontology-Based Data Access Large Language Models Ontologies CSV Gómez, Sergio Alejandro Fillottrani, Pablo Rubén Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis
topic_facet	Ciencias Informáticas Ontology-Based Data Access Large Language Models Ontologies CSV
description	In Ontology-Based Data Access (OBDA), we study how to represent legacy data sources using ontologies. This enables a modern, distributed, uniform data representation format with the ability to perform intelligent querying and processing. This task requires the development of software to interpret the data and express it as ontologies, which takes considerable time. On the other hand, large language models (LLM) have lately shown themselves to be great solution providers due to their ability to generate solutions from input specified in natural language by an end user. In this paper, we explore the potential of LLM to perform OBDA automatically. Our research hypothesis is that is possible to use an LLM tool like ChatGPT to perform OBDA. For this purpose, we studied ChatGPT responses with different problems associated with OBDA. We discovered that ChatGPT is able to generate ontologies from free text as well as from tables expressed as text or in CSV format. ChatGPT is also able to generate SPARQL queries, and it is also successful in expressing relational tables as ontologies being capable of correcting violations of integrity constraints when appropriately directed.
format	Objeto de conferencia Objeto de conferencia
author	Gómez, Sergio Alejandro Fillottrani, Pablo Rubén
author_facet	Gómez, Sergio Alejandro Fillottrani, Pablo Rubén
author_sort	Gómez, Sergio Alejandro
title	Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis
title_short	Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis
title_full	Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis
title_fullStr	Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis
title_full_unstemmed	Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis
title_sort	leveraging large language models for ontology-based data access: a preliminary analysis
publishDate	2024
url	http://sedici.unlp.edu.ar/handle/10915/176820
work_keys_str_mv	AT gomezsergioalejandro leveraginglargelanguagemodelsforontologybaseddataaccessapreliminaryanalysis AT fillottranipabloruben leveraginglargelanguagemodelsforontologybaseddataaccessapreliminaryanalysis
_version_	1845116795673903104

Leveraging Large Language Models for Ontology-Based Data Access: A Preliminary Analysis

Ejemplares similares