UNSL at eRisk 2022: decision policies with history for early classification

Autores
Loyola, Juan Martin; Thompson, Horacio Jesus; Burdisso, Sergio Gastón; Errecalde, Marcelo Luis
Año de publicación
2022
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
For the 2022 edition of the CLEF eRisk Laboratory, our research group at Universidad Nacional de San Luis (UNSL) added new approaches and improvements concerning our last participation. We proposed two decision policies for EarlyModel that take into account historic information available to the models, and incorporated two score normalization steps into the SS3 model. We also significantly reduced the runtime to process the inputs. Despite not having achieved the best performances, our team obtained the best results for the ERDE50 in tasks T1 and T2. Besides, considering the F latency, we were the third-best team for both tasks. Finally, a couple of our models got some of the best performance for the ranking-based metrics for task T1.
Fil: Loyola, Juan Martin. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis. Instituto de Matemática Aplicada de San Luis "Prof. Ezio Marchi". Universidad Nacional de San Luis. Facultad de Ciencias Físico, Matemáticas y Naturales. Instituto de Matemática Aplicada de San Luis "Prof. Ezio Marchi"; Argentina. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina
Fil: Thompson, Horacio Jesus. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina
Fil: Burdisso, Sergio Gastón. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina. Institut Dalle Molle d'intelligence artificielle perceptive; Suiza
Fil: Errecalde, Marcelo Luis. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina
Conference and Labs of the Evaluation Forum (CLEF-WN 2022)
Bologna
Italia
Università di Bologna
Materia
MACHINE LEARNING
EARLY RISK DETECTION
EARLY CLASSIFICATION
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/269451
Acceder
id CONICETDig_3f560152a1f678ceb9e3d022fe985a0d
oai_identifier_str oai:ri.conicet.gov.ar:11336/269451
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling UNSL at eRisk 2022: decision policies with history for early classificationLoyola, Juan MartinThompson, Horacio JesusBurdisso, Sergio GastónErrecalde, Marcelo LuisMACHINE LEARNINGEARLY RISK DETECTIONEARLY CLASSIFICATIONhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1For the 2022 edition of the CLEF eRisk Laboratory, our research group at Universidad Nacional de San Luis (UNSL) added new approaches and improvements concerning our last participation. We proposed two decision policies for EarlyModel that take into account historic information available to the models, and incorporated two score normalization steps into the SS3 model. We also significantly reduced the runtime to process the inputs. Despite not having achieved the best performances, our team obtained the best results for the ERDE50 in tasks T1 and T2. Besides, considering the F latency, we were the third-best team for both tasks. Finally, a couple of our models got some of the best performance for the ranking-based metrics for task T1.Fil: Loyola, Juan Martin. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis. Instituto de Matemática Aplicada de San Luis "Prof. Ezio Marchi". Universidad Nacional de San Luis. Facultad de Ciencias Físico, Matemáticas y Naturales. Instituto de Matemática Aplicada de San Luis "Prof. Ezio Marchi"; Argentina. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; ArgentinaFil: Thompson, Horacio Jesus. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; ArgentinaFil: Burdisso, Sergio Gastón. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina. Institut Dalle Molle d'intelligence artificielle perceptive; SuizaFil: Errecalde, Marcelo Luis. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; ArgentinaConference and Labs of the Evaluation Forum (CLEF-WN 2022)BolognaItaliaUniversità di BolognaRWTH Aachen University2022info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectConferenciaJournalhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/269451UNSL at eRisk 2022: decision policies with history for early classification; Conference and Labs of the Evaluation Forum (CLEF-WN 2022); Bologna; Italia; 2022; 947-9601613-0073CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://ceur-ws.org/Vol-3180/info:eu-repo/semantics/altIdentifier/url/https://ceur-ws.org/Vol-3180/paper-75.pdfInternacionalinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:02:40Zoai:ri.conicet.gov.ar:11336/269451instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:02:41.081CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv UNSL at eRisk 2022: decision policies with history for early classification
title UNSL at eRisk 2022: decision policies with history for early classification
spellingShingle UNSL at eRisk 2022: decision policies with history for early classification
Loyola, Juan Martin
MACHINE LEARNING
EARLY RISK DETECTION
EARLY CLASSIFICATION
title_short UNSL at eRisk 2022: decision policies with history for early classification
title_full UNSL at eRisk 2022: decision policies with history for early classification
title_fullStr UNSL at eRisk 2022: decision policies with history for early classification
title_full_unstemmed UNSL at eRisk 2022: decision policies with history for early classification
title_sort UNSL at eRisk 2022: decision policies with history for early classification
dc.creator.none.fl_str_mv Loyola, Juan Martin
Thompson, Horacio Jesus
Burdisso, Sergio Gastón
Errecalde, Marcelo Luis
author Loyola, Juan Martin
author_facet Loyola, Juan Martin
Thompson, Horacio Jesus
Burdisso, Sergio Gastón
Errecalde, Marcelo Luis
author_role author
author2 Thompson, Horacio Jesus
Burdisso, Sergio Gastón
Errecalde, Marcelo Luis
author2_role author
author
author
dc.subject.none.fl_str_mv MACHINE LEARNING
EARLY RISK DETECTION
EARLY CLASSIFICATION
topic MACHINE LEARNING
EARLY RISK DETECTION
EARLY CLASSIFICATION
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv For the 2022 edition of the CLEF eRisk Laboratory, our research group at Universidad Nacional de San Luis (UNSL) added new approaches and improvements concerning our last participation. We proposed two decision policies for EarlyModel that take into account historic information available to the models, and incorporated two score normalization steps into the SS3 model. We also significantly reduced the runtime to process the inputs. Despite not having achieved the best performances, our team obtained the best results for the ERDE50 in tasks T1 and T2. Besides, considering the F latency, we were the third-best team for both tasks. Finally, a couple of our models got some of the best performance for the ranking-based metrics for task T1.
Fil: Loyola, Juan Martin. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis. Instituto de Matemática Aplicada de San Luis "Prof. Ezio Marchi". Universidad Nacional de San Luis. Facultad de Ciencias Físico, Matemáticas y Naturales. Instituto de Matemática Aplicada de San Luis "Prof. Ezio Marchi"; Argentina. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina
Fil: Thompson, Horacio Jesus. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina
Fil: Burdisso, Sergio Gastón. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina. Institut Dalle Molle d'intelligence artificielle perceptive; Suiza
Fil: Errecalde, Marcelo Luis. Universidad Nacional de San Luis. Facultad de Ciencias Físico Matemáticas y Naturales. Departamento de Informática. Laboratorio Investigación y Desarrollo en Inteligencia Computacional; Argentina
Conference and Labs of the Evaluation Forum (CLEF-WN 2022)
Bologna
Italia
Università di Bologna
description For the 2022 edition of the CLEF eRisk Laboratory, our research group at Universidad Nacional de San Luis (UNSL) added new approaches and improvements concerning our last participation. We proposed two decision policies for EarlyModel that take into account historic information available to the models, and incorporated two score normalization steps into the SS3 model. We also significantly reduced the runtime to process the inputs. Despite not having achieved the best performances, our team obtained the best results for the ERDE50 in tasks T1 and T2. Besides, considering the F latency, we were the third-best team for both tasks. Finally, a couple of our models got some of the best performance for the ranking-based metrics for task T1.
publishDate 2022
dc.date.none.fl_str_mv 2022
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/conferenceObject
Conferencia
Journal
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
status_str publishedVersion
format conferenceObject
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/269451
UNSL at eRisk 2022: decision policies with history for early classification; Conference and Labs of the Evaluation Forum (CLEF-WN 2022); Bologna; Italia; 2022; 947-960
1613-0073
CONICET Digital
CONICET
url http://hdl.handle.net/11336/269451
identifier_str_mv UNSL at eRisk 2022: decision policies with history for early classification; Conference and Labs of the Evaluation Forum (CLEF-WN 2022); Bologna; Italia; 2022; 947-960
1613-0073
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://ceur-ws.org/Vol-3180/
info:eu-repo/semantics/altIdentifier/url/https://ceur-ws.org/Vol-3180/paper-75.pdf
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.coverage.none.fl_str_mv Internacional
dc.publisher.none.fl_str_mv RWTH Aachen University
publisher.none.fl_str_mv RWTH Aachen University
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613833560162304
score 13.069144

Publicaciones similares