Mostra el registre d'ítem simple

dc.contributor.authorBasta, Christine Raouf Saad
dc.contributor.authorRuiz Costa-Jussà, Marta
dc.contributor.authorRodríguez Fonollosa, José Adrián
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Teoria del Senyal i Comunicacions
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2020-11-19T11:59:10Z
dc.date.available2020-11-19T11:59:10Z
dc.date.issued2020
dc.identifier.citationBasta, C.; Costa-jussà, M.R.; Fonollosa, J.A.R. Towards mitigating gender bias in a decoder-based neural machine translation model by adding contextual information. A: Widening Natural Language Processing Workshop. "Proceedings of the The Fourth Widening Natural Language Processing Workshop". Stroudsburg, PA: Association for Computational Linguistics, 2020, p. 99-102. ISBN 978-1-952148-06-4. DOI 10.18653/v1/2020.winlp-1.25.
dc.identifier.isbn978-1-952148-06-4
dc.identifier.urihttp://hdl.handle.net/2117/332581
dc.description.abstractGender bias negatively impacts many natural language processing applications, including ma-chine translation (MT). The motivation behind this work is to study whether recent proposedMT techniques are significantly contributing to attenuate biases in document-level and gender-balanced data. For the study, we consider approaches of adding the previous sentence and thespeaker information, implemented in a decoder-based neural MT system. We show improve-ments both in translation quality (+1 BLEU point) as well as in gender bias mitigation onWinoMT (+5% accuracy).
dc.description.sponsorshipThis work is supported in part by the Catalan Agency for Management of University and Research Grants (AGAUR) through the FI PhD Scholarship. This work is also supported in part by the Spanish Ministerio de Economía y Competitividad, the European Regional Development Fund and the Agencia Estatal de Investigacion, through the postdoctoral senior grant Ramón y Cajal, contract TEC2015-69266-P (MINECO/FEDER,EU) and contract PCIN-2017-079 (AEI/MINECO).
dc.format.extent4 p.
dc.language.isoeng
dc.publisherAssociation for Computational Linguistics
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic
dc.subject.lcshNatural language processing (Computer science)
dc.subject.lcshMachine translating
dc.subject.lcshMachine learning
dc.subject.lcshSexism in language
dc.titleTowards mitigating gender bias in a decoder-based neural machine translation model by adding contextual information
dc.typeConference report
dc.subject.lemacTractament del llenguatge natural
dc.subject.lemacTraducció automàtica
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacSexisme en el llenguatge
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.identifier.doi10.18653/v1/2020.winlp-1.25
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://www.aclweb.org/anthology/2020.winlp-1.25/
dc.rights.accessOpen Access
local.identifier.drac28881185
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO//TEC2015-69266-P/ES/TECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ Y AUDIO/
dc.relation.projectidinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación (PEICTI) 2013-2016/PCIN-2017-079/ES/AUTONOMOUS LIFELONG LEARNING INTELLIGENT SYSTEMS/
local.citation.authorBasta, C.; Ruíz, M.; Rodríguez, J.A
local.citation.contributorWidening Natural Language Processing Workshop
local.citation.pubplaceStroudsburg, PA
local.citation.publicationNameProceedings of the The Fourth Widening Natural Language Processing Workshop
local.citation.startingPage99
local.citation.endingPage102


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple