Legal NERC with ontologies, Wikipedia and curriculum learning

Ponencia presentada en la 15th European Chapter of the Association for Computational Linguistics (EACL 2017), 2017, Valencia, Spain. pp.254 - 259, 2017.

Detalles Bibliográficos
Autores principales: Cardellino, Cristian, Teruel, Milagro, Alonso Alemany, Laura, Villata, Serena
Formato: conferenceObject
Lenguaje:Inglés
Publicado: 2024
Materias:
Acceso en línea:http://hdl.handle.net/11086/552665
Aporte de:
id I10-R141-11086-552665
record_format dspace
spelling I10-R141-11086-5526652024-09-10T17:10:35Z Legal NERC with ontologies, Wikipedia and curriculum learning Cardellino, Cristian Teruel, Milagro Alonso Alemany, Laura Villata, Serena Ontologies Natural language processing Legal informatics Information extraction Ponencia presentada en la 15th European Chapter of the Association for Computational Linguistics (EACL 2017), 2017, Valencia, Spain. pp.254 - 259, 2017. 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: Villata, Serena. Universite Cote d’Azur; France. In this paper, we present a Wikipediabased approach to develop resources for the legal domain. We establish a mapping between a legal domain ontology, LKIF (Hoekstra et al., 2007), and a Wikipediabased ontology, YAGO (Suchanek et al., 2007), and through that we populate LKIF. Moreover, we use the mentions of those entities in Wikipedia text to train a specific Named Entity Recognizer and Classifier. We find that this classifier works well in the Wikipedia, but, as could be expected, performance decreases in a corpus of judgments of the European Court of Human Rights. However, this tool will be used as a preprocess for human annotation. We resort to a technique called curriculum learning aimed to overcome problems of overfitting by learning increasingly more complex concepts. However, we find that in this particular setting, the method works best by learning from most specific to most general concepts, not the other way round. http://aclanthology.info/papers/E17-2041/legal-nerc-with-ontologies-wikipedia-and-curriculum-learning 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: Villata, Serena. Universite Cote d’Azur; France. Otras Ciencias de la Computación e Información 2024-07-10T18:42:23Z 2024-07-10T18:42:23Z 2017 conferenceObject http://hdl.handle.net/11086/552665 eng https://hal.science/hal-01572444 Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ Electrónico y/o Digital
institution Universidad Nacional de Córdoba
institution_str I-10
repository_str R-141
collection Repositorio Digital Universitario (UNC)
language Inglés
topic Ontologies
Natural language processing
Legal informatics
Information extraction
spellingShingle Ontologies
Natural language processing
Legal informatics
Information extraction
Cardellino, Cristian
Teruel, Milagro
Alonso Alemany, Laura
Villata, Serena
Legal NERC with ontologies, Wikipedia and curriculum learning
topic_facet Ontologies
Natural language processing
Legal informatics
Information extraction
description Ponencia presentada en la 15th European Chapter of the Association for Computational Linguistics (EACL 2017), 2017, Valencia, Spain. pp.254 - 259, 2017.
format conferenceObject
author Cardellino, Cristian
Teruel, Milagro
Alonso Alemany, Laura
Villata, Serena
author_facet Cardellino, Cristian
Teruel, Milagro
Alonso Alemany, Laura
Villata, Serena
author_sort Cardellino, Cristian
title Legal NERC with ontologies, Wikipedia and curriculum learning
title_short Legal NERC with ontologies, Wikipedia and curriculum learning
title_full Legal NERC with ontologies, Wikipedia and curriculum learning
title_fullStr Legal NERC with ontologies, Wikipedia and curriculum learning
title_full_unstemmed Legal NERC with ontologies, Wikipedia and curriculum learning
title_sort legal nerc with ontologies, wikipedia and curriculum learning
publishDate 2024
url http://hdl.handle.net/11086/552665
work_keys_str_mv AT cardellinocristian legalnercwithontologieswikipediaandcurriculumlearning
AT teruelmilagro legalnercwithontologieswikipediaandcurriculumlearning
AT alonsoalemanylaura legalnercwithontologieswikipediaandcurriculumlearning
AT villataserena legalnercwithontologieswikipediaandcurriculumlearning
_version_ 1824552237522747392