Using robustness to learn to order semantic properties in referring expression generation

Slides de ponencia presentada en Advances in Artificial Intelligence - IBERAMIA 2016. San José, Costa Rica 23-25, November 2016.

Detalles Bibliográficos
Autores principales: Duboué, Pablo Ariel, Domínguez, Martín Ariel
Formato: submittedVersion conferenceObject
Lenguaje:Inglés
Publicado: 2023
Materias:
Semantc order
Referring expression
Robustness
Acceso en línea:http://hdl.handle.net/11086/548254
Aporte de:
Repositorio Digital Universitario (UNC) de Universidad Nacional de Córdoba
id I10-R141-11086-548254
record_format dspace
spelling I10-R141-11086-5482542023-08-31T13:16:33Z Using robustness to learn to order semantic properties in referring expression generation Duboué, Pablo Ariel Domínguez, Martín Ariel Semantc order Referring expression Robustness Slides de ponencia presentada en Advances in Artificial Intelligence - IBERAMIA 2016. San José, Costa Rica 23-25, November 2016. submittedVersion Fil: Duboué, Pablo Ariel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Domínguez, Martín Ariel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. A sub-task of Natural Language Generation (NLG) is the generation of referring expressions (REG). REG algorithms aim to select attributes that unambiguously identify an entity with respect to a set of distractors. Previous work has defined a methodology to evaluate REG algorithms using real life examples with naturally occurring alterations in the properties of referring entities. It has been found that REG algorithms have key parameters tuned to exhibit a large degree of robustness. Using this insight, we present here experiments for learning the order of semantic properties used by a high performing REG algorithm. Presenting experiments on two types of entities (people and organizations) and using different versions of DBpedia (a freely available knowledge base containing information extracted from Wikipedia pages) we found that robustness of the tuned algorithm and its parameters do coincide but more work is needed to learn these parameters from data in a generalizable fashion. http://link.springer.com/chapter/10.1007/978-3-319-47955-2_14 submittedVersion Fil: Duboué, Pablo Ariel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Fil: Domínguez, Martín Ariel. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación; Argentina. Ciencias de la Computación 2023-07-25T20:12:18Z 2023-07-25T20:12:18Z 2016 conferenceObject http://hdl.handle.net/11086/548254 eng Del artículo publicado: https://doi.org/10.1007/978-3-319-47955-2_14 Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ Impreso; 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 Semantc order
Referring expression
Robustness
spellingShingle Semantc order
Referring expression
Robustness
Duboué, Pablo Ariel
Domínguez, Martín Ariel
Using robustness to learn to order semantic properties in referring expression generation
topic_facet Semantc order
Referring expression
Robustness
description Slides de ponencia presentada en Advances in Artificial Intelligence - IBERAMIA 2016. San José, Costa Rica 23-25, November 2016.
format submittedVersion
conferenceObject
author Duboué, Pablo Ariel
Domínguez, Martín Ariel
author_facet Duboué, Pablo Ariel
Domínguez, Martín Ariel
author_sort Duboué, Pablo Ariel
title Using robustness to learn to order semantic properties in referring expression generation
title_short Using robustness to learn to order semantic properties in referring expression generation
title_full Using robustness to learn to order semantic properties in referring expression generation
title_fullStr Using robustness to learn to order semantic properties in referring expression generation
title_full_unstemmed Using robustness to learn to order semantic properties in referring expression generation
title_sort using robustness to learn to order semantic properties in referring expression generation
publishDate 2023
url http://hdl.handle.net/11086/548254
work_keys_str_mv AT dubouepabloariel usingrobustnesstolearntoordersemanticpropertiesinreferringexpressiongeneration
AT dominguezmartinariel usingrobustnesstolearntoordersemanticpropertiesinreferringexpressiongeneration
_version_ 1782014777502990336

Ejemplares similares