Mostra el registre d'ítem simple
Extensive study on the underlying gender bias in contextualized word embeddings
dc.contributor.author | Basta, Christine Raouf Saad |
dc.contributor.author | Ruiz Costa-Jussà, Marta |
dc.contributor.author | Casas Manzanares, Noé |
dc.contributor.other | Universitat Politècnica de Catalunya. Doctorat en Teoria del Senyal i Comunicacions |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.date.accessioned | 2020-12-21T09:28:13Z |
dc.date.issued | 2021-04 |
dc.identifier.citation | Basta, C.; Costa-jussà, M.R.; Casas, N. Extensive study on the underlying gender bias in contextualized word embeddings. "Neural computing and applications", Abril 2021, vol. 33, p. 3371-3384. |
dc.identifier.issn | 0941-0643 |
dc.identifier.uri | http://hdl.handle.net/2117/334693 |
dc.description.abstract | Gender bias is affecting many natural language processing applications. While we are still far from proposing debiasing methods that will solve the problem, we are making progress analyzing the impact of this bias in current algorithms. This paper provides an extensive study of the underlying gender bias in popular contextualized word embeddings. Our study provides an insightful analysis of evaluation measures applied to several English data domains and the layers of the contextualized word embeddings. It is also adapted and extended to the Spanish language. Our study points out the advantages and limitations of the various evaluation measures that we are using and aims to standardize the evaluation of gender bias in contextualized word embeddings. |
dc.description.sponsorship | This work is supported in part by the Catalan Agency for Management of University and Research Grants (AGAUR) through the FI PhD Scholarship and the Industrial PhD Grant. This work also is supported in part by the Spanish Ministerio de Economía y Competitividad, the European Regional Development Fund, the Agencia Estatal de Investigación through the postdoctoral senior grant Ramón y Cajal and the Projects EUR2019-103819, PCIN-2017-079 and PID2019-107579RB-I00. |
dc.format.extent | 14 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic |
dc.subject.lcsh | Natural language processing (Computer science) |
dc.subject.lcsh | Sexism in language |
dc.subject.other | Gender bias |
dc.subject.other | Contextualized embeddings |
dc.title | Extensive study on the underlying gender bias in contextualized word embeddings |
dc.type | Article |
dc.subject.lemac | Tractament del llenguatge natural (Informàtica) |
dc.subject.lemac | Sexisme en el llenguatge |
dc.contributor.group | Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
dc.identifier.doi | 10.1007/s00521-020-05211-z |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://link.springer.com/article/10.1007/s00521-020-05211-z |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 28881139 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/AEI/2PE/EUR2019-103819 |
dc.relation.projectid | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-107579RB-I00/ES/ARQUITECTURAS AVANZADAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ, AUDIO Y LENGUAJE/ |
dc.relation.projectid | info: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/ |
dc.date.lift | 10000-01-01 |
local.citation.author | Basta, C.; Costa-jussà, Marta R.; Casas, N. |
local.citation.publicationName | Neural computing and applications |
local.citation.volume | 33 |
local.citation.startingPage | 3371 |
local.citation.endingPage | 3384 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [1.049]
-
Articles de revista [172]
-
Articles de revista [211]