Learning slowly to learn better : curriculum learning for legal ontology population

Autores
Cardellino, Cristian; Teruel, Milagro; Alonso Alemany, Laura; Villata, Serena
Año de publicación
2017
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Ponencia presentada Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society Conference
Fil: Cardellino, Cristian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Teruel, Milagro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universite Cote d’Azur; France.
In this paper, we present an ontology population approach for legal ontologies. We exploit Wikipedia as a source of manually annotated examples of legal entities. We align YAGO, a Wikipedia-based ontology, and LKIF, an ontology specifically designed for the legal domain. Through this alignment, we can effectively populate the LKIF ontology, with the aim to obtain examples to train a Named Entity Recognizer and Classifier to be used for finding and classifying entities in legal texts. Since examples of annotated data in the legal domain are very few, we apply a machine learning strategy called curriculum learning aimed to overcome problems of overfitting by learning increasingly more complex concepts. We compare the performance of this method to identify Named Entities with respect to batch learning as well as two other baselines. Results are satisfying and foster further research in this direction.
https://aaai.org/ocs/index.php/FLAIRS/FLAIRS17/paper/view/15526
Fil: Cardellino, Cristian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Teruel, Milagro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universite Cote d’Azur; France.
Otras Ciencias de la Computación e Información
Materia
Ontologías
Procesamiento del lenguaje natural
Informática legal
Deep learning
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Repositorio
Repositorio Digital Universitario (UNC)
Institución
Universidad Nacional de Córdoba
OAI Identificador
oai:rdu.unc.edu.ar:11086/552703
Acceder
id RDUUNC_9cbc36bc9db428d6d74b44237599d4c8
oai_identifier_str oai:rdu.unc.edu.ar:11086/552703
network_acronym_str RDUUNC
repository_id_str 2572
network_name_str Repositorio Digital Universitario (UNC)
spelling Learning slowly to learn better : curriculum learning for legal ontology populationCardellino, CristianTeruel, MilagroAlonso Alemany, LauraVillata, SerenaOntologíasProcesamiento del lenguaje naturalInformática legalDeep learningPonencia presentada Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society ConferenceFil: Cardellino, Cristian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.Fil: Teruel, Milagro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.Fil: Alonso Alemany, Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.Fil: Alonso Alemany, Laura. Universite Cote d’Azur; France.In this paper, we present an ontology population approach for legal ontologies. We exploit Wikipedia as a source of manually annotated examples of legal entities. We align YAGO, a Wikipedia-based ontology, and LKIF, an ontology specifically designed for the legal domain. Through this alignment, we can effectively populate the LKIF ontology, with the aim to obtain examples to train a Named Entity Recognizer and Classifier to be used for finding and classifying entities in legal texts. Since examples of annotated data in the legal domain are very few, we apply a machine learning strategy called curriculum learning aimed to overcome problems of overfitting by learning increasingly more complex concepts. We compare the performance of this method to identify Named Entities with respect to batch learning as well as two other baselines. Results are satisfying and foster further research in this direction.https://aaai.org/ocs/index.php/FLAIRS/FLAIRS17/paper/view/15526Fil: Cardellino, Cristian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.Fil: Teruel, Milagro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.Fil: Alonso Alemany, Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.Fil: Alonso Alemany, Laura. Universite Cote d’Azur; France.Otras Ciencias de la Computación e Información2017info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf978-157735787-2http://hdl.handle.net/11086/552703enginfo:eu-repo/semantics/openAccessreponame:Repositorio Digital Universitario (UNC)instname:Universidad Nacional de Córdobainstacron:UNC2025-09-29T13:43:32Zoai:rdu.unc.edu.ar:11086/552703Institucionalhttps://rdu.unc.edu.ar/Universidad públicaNo correspondehttp://rdu.unc.edu.ar/oai/snrdoca.unc@gmail.comArgentinaNo correspondeNo correspondeNo correspondeopendoar:25722025-09-29 13:43:33.239Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdobafalse
dc.title.none.fl_str_mv Learning slowly to learn better : curriculum learning for legal ontology population
title Learning slowly to learn better : curriculum learning for legal ontology population
spellingShingle Learning slowly to learn better : curriculum learning for legal ontology population
Cardellino, Cristian
Ontologías
Procesamiento del lenguaje natural
Informática legal
Deep learning
title_short Learning slowly to learn better : curriculum learning for legal ontology population
title_full Learning slowly to learn better : curriculum learning for legal ontology population
title_fullStr Learning slowly to learn better : curriculum learning for legal ontology population
title_full_unstemmed Learning slowly to learn better : curriculum learning for legal ontology population
title_sort Learning slowly to learn better : curriculum learning for legal ontology population
dc.creator.none.fl_str_mv Cardellino, Cristian
Teruel, Milagro
Alonso Alemany, Laura
Villata, Serena
author Cardellino, Cristian
author_facet Cardellino, Cristian
Teruel, Milagro
Alonso Alemany, Laura
Villata, Serena
author_role author
author2 Teruel, Milagro
Alonso Alemany, Laura
Villata, Serena
author2_role author
author
author
dc.subject.none.fl_str_mv Ontologías
Procesamiento del lenguaje natural
Informática legal
Deep learning
topic Ontologías
Procesamiento del lenguaje natural
Informática legal
Deep learning
dc.description.none.fl_txt_mv Ponencia presentada Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society Conference
Fil: Cardellino, Cristian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Teruel, Milagro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universite Cote d’Azur; France.
In this paper, we present an ontology population approach for legal ontologies. We exploit Wikipedia as a source of manually annotated examples of legal entities. We align YAGO, a Wikipedia-based ontology, and LKIF, an ontology specifically designed for the legal domain. Through this alignment, we can effectively populate the LKIF ontology, with the aim to obtain examples to train a Named Entity Recognizer and Classifier to be used for finding and classifying entities in legal texts. Since examples of annotated data in the legal domain are very few, we apply a machine learning strategy called curriculum learning aimed to overcome problems of overfitting by learning increasingly more complex concepts. We compare the performance of this method to identify Named Entities with respect to batch learning as well as two other baselines. Results are satisfying and foster further research in this direction.
https://aaai.org/ocs/index.php/FLAIRS/FLAIRS17/paper/view/15526
Fil: Cardellino, Cristian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Teruel, Milagro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina.
Fil: Alonso Alemany, Laura. Universite Cote d’Azur; France.
Otras Ciencias de la Computación e Información
description Ponencia presentada Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society Conference
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv 978-157735787-2
http://hdl.handle.net/11086/552703
identifier_str_mv 978-157735787-2
url http://hdl.handle.net/11086/552703
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositorio Digital Universitario (UNC)
instname:Universidad Nacional de Córdoba
instacron:UNC
reponame_str Repositorio Digital Universitario (UNC)
collection Repositorio Digital Universitario (UNC)
instname_str Universidad Nacional de Córdoba
instacron_str UNC
institution UNC
repository.name.fl_str_mv Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdoba
repository.mail.fl_str_mv oca.unc@gmail.com
_version_ 1844618959004893184
score 13.070432

Publicaciones similares