Argumentative Conversational Agents for Explainable Artificial Intelligence

Recent years have witnessed a striking rise of artificial intelligence algorithms that are able to show outstanding performance. However, such good performance is oftentimes achieved at the expense of explainability. Not only can the lack of algorithmic explainability undermine the user's trust...

Descripción completa

Detalles Bibliográficos
Autor: Stepin, Ilia
Tipo de recurso: tesis doctoral
Fecha de publicación:2023
País:España
Institución:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:minerva.usc.gal:10347/31084
Acceso en línea:http://hdl.handle.net/10347/31084
Access Level:acceso abierto
Palabra clave:120304 Inteligencia artificial
120317 Informática
570104 Lingüística informatizada
Descripción
Sumario:Recent years have witnessed a striking rise of artificial intelligence algorithms that are able to show outstanding performance. However, such good performance is oftentimes achieved at the expense of explainability. Not only can the lack of algorithmic explainability undermine the user's trust in the algorithmic output, but it can also cause adverse consequences. In this thesis, we advocate the use of interpretable rule-based models that can serve both as stand-alone applications and proxies for black-box models. More specifically, we design an explanation generation framework that outputs contrastive, selected, and social explanations for interpretable (decision trees and rule-based) classifiers. We show that the resulting explanations enhance the effectiveness of AI algorithms while preserving their transparent structure.