Detalhes bibliográficos
| Ano de defesa: |
2024 |
| Autor(a) principal: |
Sousa, Carlos Eduardo Lemos de
 |
| Orientador(a): |
Nöth, Winfried
|
| Banca de defesa: |
Não Informado pela instituição |
| Tipo de documento: |
Dissertação
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
por |
| Instituição de defesa: |
Pontifícia Universidade Católica de São Paulo
|
| Programa de Pós-Graduação: |
Programa de Pós-Graduação em Tecnologias da Inteligência e Design Digital
|
| Departamento: |
Faculdade de Ciências Exatas e Tecnologia
|
| País: |
Brasil
|
| Palavras-chave em Português: |
|
| Palavras-chave em Inglês: |
|
| Área do conhecimento CNPq: |
|
| Link de acesso: |
https://repositorio.pucsp.br/jspui/handle/handle/41778
|
Resumo: |
This research explores the challenge of incorporating commonsense knowledge into Artificial Intelligence (AI) systems, aiming to improve their ability to perform natural language processing tasks such as understanding text, generating responses, and resolving ambiguities. Through a methodology that included comprehensive literature analysis, critical evaluation of existing research, and analysis of simulated cases on the main AI platforms on the market, the study identified that, despite significant technological advances, there are still substantial gaps and challenges in effective integration. of commonsense knowledge in AI systems. The results point to the need for combined strategies, involving ontologies, knowledge databases, and advanced machine learning techniques, to achieve a more efficient understanding and application of commonsense by AI systems. The conclusion of the work emphasizes the importance of interdisciplinary and ethical approaches in the development of AI, highlighting that, to achieve truly autonomous and efficient systems, it is essential that they can interpret and react in an adaptive and sensitive way to the nuances of commonsense human knowledge |
