Evaluation of a refinement algorithm for the generation of referring expressions

Autores
Altamirano, Ivana Romina; Benotti, Luciana
Año de publicación
2013
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
In this paper we describe and evaluate an algorithm for generating referring expressions that uses linear regression for learning the probability of using certain properties to describe an object in a given scene. The algorithm we present is an extension of a refinement algorithm modified to take probabilities learnt from corpora into account. As a result, the algorithm is able not only to generate correct referring expressions that uniquely identify the referents but it also generates referring expressions that are considered equal or better than those generated by humans in 92% of the cases by a human judge. We classify and give examples of the referring expressions that humans prefer, and indicate the potential impact of our work for theories of the egocentric use of language.
Fil: Altamirano, Ivana Romina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Benotti, Luciana. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física. Sección Física; Argentina
Materia
Evaluation
Machine Learning
Refinement Algorithms
Referring Expressions
Human Judge
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:11336/80139

id CONICETDig_efcaad56db3db4d365618b07cabdf4b4
oai_identifier_str oai:ri.conicet.gov.ar:11336/80139
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Evaluation of a refinement algorithm for the generation of referring expressionsAltamirano, Ivana RominaBenotti, LucianaEvaluationMachine LearningRefinement AlgorithmsReferring ExpressionsHuman Judgehttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1In this paper we describe and evaluate an algorithm for generating referring expressions that uses linear regression for learning the probability of using certain properties to describe an object in a given scene. The algorithm we present is an extension of a refinement algorithm modified to take probabilities learnt from corpora into account. As a result, the algorithm is able not only to generate correct referring expressions that uniquely identify the referents but it also generates referring expressions that are considered equal or better than those generated by humans in 92% of the cases by a human judge. We classify and give examples of the referring expressions that humans prefer, and indicate the potential impact of our work for theories of the egocentric use of language.Fil: Altamirano, Ivana Romina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; ArgentinaFil: Benotti, Luciana. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física. Sección Física; ArgentinaSpringer2013-10info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/80139Altamirano, Ivana Romina; Benotti, Luciana; Evaluation of a refinement algorithm for the generation of referring expressions; Springer; Lecture Notes in Computer Science; 8175 LNAI; 10-2013; 31-440302-9743CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/http://link.springer.com/chapter/10.1007%2F978-3-642-40972-1_3info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-642-40972-1_3info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-02-06T13:18:51Zoai:ri.conicet.gov.ar:11336/80139instacron: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:34982026-02-06 13:18:51.539CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Evaluation of a refinement algorithm for the generation of referring expressions
title Evaluation of a refinement algorithm for the generation of referring expressions
spellingShingle Evaluation of a refinement algorithm for the generation of referring expressions
Altamirano, Ivana Romina
Evaluation
Machine Learning
Refinement Algorithms
Referring Expressions
Human Judge
title_short Evaluation of a refinement algorithm for the generation of referring expressions
title_full Evaluation of a refinement algorithm for the generation of referring expressions
title_fullStr Evaluation of a refinement algorithm for the generation of referring expressions
title_full_unstemmed Evaluation of a refinement algorithm for the generation of referring expressions
title_sort Evaluation of a refinement algorithm for the generation of referring expressions
dc.creator.none.fl_str_mv Altamirano, Ivana Romina
Benotti, Luciana
author Altamirano, Ivana Romina
author_facet Altamirano, Ivana Romina
Benotti, Luciana
author_role author
author2 Benotti, Luciana
author2_role author
dc.subject.none.fl_str_mv Evaluation
Machine Learning
Refinement Algorithms
Referring Expressions
Human Judge
topic Evaluation
Machine Learning
Refinement Algorithms
Referring Expressions
Human Judge
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv In this paper we describe and evaluate an algorithm for generating referring expressions that uses linear regression for learning the probability of using certain properties to describe an object in a given scene. The algorithm we present is an extension of a refinement algorithm modified to take probabilities learnt from corpora into account. As a result, the algorithm is able not only to generate correct referring expressions that uniquely identify the referents but it also generates referring expressions that are considered equal or better than those generated by humans in 92% of the cases by a human judge. We classify and give examples of the referring expressions that humans prefer, and indicate the potential impact of our work for theories of the egocentric use of language.
Fil: Altamirano, Ivana Romina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Benotti, Luciana. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física. Sección Física; Argentina
description In this paper we describe and evaluate an algorithm for generating referring expressions that uses linear regression for learning the probability of using certain properties to describe an object in a given scene. The algorithm we present is an extension of a refinement algorithm modified to take probabilities learnt from corpora into account. As a result, the algorithm is able not only to generate correct referring expressions that uniquely identify the referents but it also generates referring expressions that are considered equal or better than those generated by humans in 92% of the cases by a human judge. We classify and give examples of the referring expressions that humans prefer, and indicate the potential impact of our work for theories of the egocentric use of language.
publishDate 2013
dc.date.none.fl_str_mv 2013-10
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/80139
Altamirano, Ivana Romina; Benotti, Luciana; Evaluation of a refinement algorithm for the generation of referring expressions; Springer; Lecture Notes in Computer Science; 8175 LNAI; 10-2013; 31-44
0302-9743
CONICET Digital
CONICET
url http://hdl.handle.net/11336/80139
identifier_str_mv Altamirano, Ivana Romina; Benotti, Luciana; Evaluation of a refinement algorithm for the generation of referring expressions; Springer; Lecture Notes in Computer Science; 8175 LNAI; 10-2013; 31-44
0302-9743
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://link.springer.com/chapter/10.1007%2F978-3-642-40972-1_3
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-642-40972-1_3
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.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
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_ 1856403473899192320
score 13.115731