RUJA: Repositorio Institucional de Producción Científica

 

A Survey on Bias in Deep NLP

dc.contributor.authorGarrido-Muñoz, Ismael
dc.contributor.authorMontejo-Ráez, Arturo
dc.contributor.authorMartínez-Santiago, Fernando
dc.contributor.authorUreña-López, L. Alfonso
dc.date.accessioned2024-02-03T11:25:58Z
dc.date.available2024-02-03T11:25:58Z
dc.date.issued2021-04-02
dc.description.abstractDeep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (also known as “pre-training”), versatile and performing models are released continuously for every new network design. These networks, somehow, learn a probability distribution of words and relations across the training collection used, inheriting the potential flaws, inconsistencies and biases contained in such a collection. As pre-trained models have been found to be very useful approaches to transfer learning, dealing with bias has become a relevant issue in this new scenario. We introduce bias in a formal way and explore how it has been treated in several networks, in terms of detection and correction. In addition, available resources are identified and a strategy to deal with bias in deep NLP is proposed.es_ES
dc.description.sponsorshipThis study is partially funded by the Spanish Government under the LIVING-LANG project (RTI2018-094653-B-C21).es_ES
dc.identifier.citationGarrido-Muñoz , I.; Montejo-Ráez , A.; Martínez-Santiago , F.; Ureña-López , L.A. A Survey on Bias in Deep NLP. Appl. Sci. 2021, 11, 3184. https://doi.org/10.3390/app11073184es_ES
dc.identifier.issn2076-3417es_ES
dc.identifier.otherhttps://doi.org/10.3390/app11073184es_ES
dc.identifier.urihttps://www.mdpi.com/2076-3417/11/7/3184es_ES
dc.identifier.urihttps://hdl.handle.net/10953/1991
dc.language.isoenges_ES
dc.publisherMDPIes_ES
dc.relation.ispartofApplied Scienceses_ES
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses_ES
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subjectnatural language processinges_ES
dc.subjectdeep learninges_ES
dc.subjectbiased modelses_ES
dc.titleA Survey on Bias in Deep NLPes_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.type.versioninfo:eu-repo/semantics/publishedVersiones_ES

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
2021_SurveyBiasDeepNLP.pdf
Tamaño:
399.7 KB
Formato:
Adobe Portable Document Format
Descripción:
Published version

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.98 KB
Formato:
Item-specific license agreed upon to submission
Descripción:

Colecciones