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
id ES_b76fd8d3776ea8b806639682c8f8fc79
oai_identifier_str oai:minerva.usc.gal:10347/31084
network_acronym_str ES
network_name_str España
repository_id_str
spelling Argumentative Conversational Agents for Explainable Artificial IntelligenceStepin, Ilia120304 Inteligencia artificial120317 Informática570104 Lingüística informatizadaRecent 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.Alonso Moral, José MaríaCatalá Bolós, AlejandroUniversidade de Santiago de Compostela. Escola de Doutoramento Internacional (EDIUS)20232023-01-0120232023-01-01doctoral thesishttp://purl.org/coar/resource_type/c_db06info:eu-repo/semantics/doctoralThesisapplication/pdfhttp://hdl.handle.net/10347/31084reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostelainstname:Universidad de Santiago de Compostela (USC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:minerva.usc.gal:10347/310842026-06-15T12:47:27Z
dc.title.none.fl_str_mv Argumentative Conversational Agents for Explainable Artificial Intelligence
title Argumentative Conversational Agents for Explainable Artificial Intelligence
spellingShingle Argumentative Conversational Agents for Explainable Artificial Intelligence
Stepin, Ilia
120304 Inteligencia artificial
120317 Informática
570104 Lingüística informatizada
title_short Argumentative Conversational Agents for Explainable Artificial Intelligence
title_full Argumentative Conversational Agents for Explainable Artificial Intelligence
title_fullStr Argumentative Conversational Agents for Explainable Artificial Intelligence
title_full_unstemmed Argumentative Conversational Agents for Explainable Artificial Intelligence
title_sort Argumentative Conversational Agents for Explainable Artificial Intelligence
dc.creator.none.fl_str_mv Stepin, Ilia
author Stepin, Ilia
author_facet Stepin, Ilia
author_role author
dc.contributor.none.fl_str_mv Alonso Moral, José María
Catalá Bolós, Alejandro
Universidade de Santiago de Compostela. Escola de Doutoramento Internacional (EDIUS)
dc.subject.none.fl_str_mv 120304 Inteligencia artificial
120317 Informática
570104 Lingüística informatizada
topic 120304 Inteligencia artificial
120317 Informática
570104 Lingüística informatizada
description 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.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023-01-01
2023
2023-01-01
dc.type.none.fl_str_mv doctoral thesis
http://purl.org/coar/resource_type/c_db06
dc.type.openaire.fl_str_mv info:eu-repo/semantics/doctoralThesis
format doctoralThesis
dc.identifier.none.fl_str_mv http://hdl.handle.net/10347/31084
url http://hdl.handle.net/10347/31084
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
instname:Universidad de Santiago de Compostela (USC)
instname_str Universidad de Santiago de Compostela (USC)
reponame_str Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
collection Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417529226559488
score 15,811543

Similares en LA Referencia