A tool to overcome technical barriers for bias assessment in human language technologies

Autores
Alemany, Laura Alonso; Benotti, Luciana; Gonzalez, Lucía; Maina, Hernán Javier; Busaniche, Beatriz; Halvorsen, Alexia; Bordone, Matías; Sanchez, Jorge Adrian
Año de publicación
2022
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Automatic processing of language is becoming pervasive in our lives, oftentaking central roles in our decision making, like choosing the wording for ourmessages and mails, translating our readings, or even having full conversationswith us. Word embeddings are a key component of modern natural languageprocessing systems. They provide a representation of words that has boosted theperformance of many applications, working as a semblance of meaning. Wordembeddings seem to capture a semblance of the meaning of words from raw text,but, at the same time, they also distill stereotypes and societal biases whichare subsequently relayed to the final applications. Such biases can bediscriminatory. It is very important to detect and mitigate those biases, toprevent discriminatory behaviors of automated processes, which can be much moreharmful than in the case of humans because their of their scale. There arecurrently many tools and techniques to detect and mitigate biases in wordembeddings, but they present many barriers for the engagement of people withouttechnical skills. As it happens, most of the experts in bias, either socialscientists or people with deep knowledge of the context where bias is harmful,do not have such skills, and they cannot engage in the processes of biasdetection because of the technical barriers. We have studied the barriers inexisting tools and have explored their possibilities and limitations withdifferent kinds of users. With this exploration, we propose to develop a toolthat is specially aimed to lower the technical barriers and provide theexploration power to address the requirements of experts, scientists and peoplein general who are willing to audit these technologies.
Fil: Alemany, Laura Alonso. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Benotti, Luciana. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Gonzalez, Lucía. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Maina, Hernán Javier. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Busaniche, Beatriz. Fundación Via Libre; Argentina
Fil: Halvorsen, Alexia. Fundación Via Libre; Argentina
Fil: Bordone, Matías. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Sanchez, Jorge Adrian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Materia
Natural Language Processing
Language Models
Bias
Stereotypes and Discrimination
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/211790

id CONICETDig_4e603ec864b3f0bdcc4a82691506239d
oai_identifier_str oai:ri.conicet.gov.ar:11336/211790
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling A tool to overcome technical barriers for bias assessment in human language technologiesAlemany, Laura AlonsoBenotti, LucianaGonzalez, LucíaMaina, Hernán JavierBusaniche, BeatrizHalvorsen, AlexiaBordone, MatíasSanchez, Jorge AdrianNatural Language ProcessingLanguage ModelsBiasStereotypes and Discriminationhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Automatic processing of language is becoming pervasive in our lives, oftentaking central roles in our decision making, like choosing the wording for ourmessages and mails, translating our readings, or even having full conversationswith us. Word embeddings are a key component of modern natural languageprocessing systems. They provide a representation of words that has boosted theperformance of many applications, working as a semblance of meaning. Wordembeddings seem to capture a semblance of the meaning of words from raw text,but, at the same time, they also distill stereotypes and societal biases whichare subsequently relayed to the final applications. Such biases can bediscriminatory. It is very important to detect and mitigate those biases, toprevent discriminatory behaviors of automated processes, which can be much moreharmful than in the case of humans because their of their scale. There arecurrently many tools and techniques to detect and mitigate biases in wordembeddings, but they present many barriers for the engagement of people withouttechnical skills. As it happens, most of the experts in bias, either socialscientists or people with deep knowledge of the context where bias is harmful,do not have such skills, and they cannot engage in the processes of biasdetection because of the technical barriers. We have studied the barriers inexisting tools and have explored their possibilities and limitations withdifferent kinds of users. With this exploration, we propose to develop a toolthat is specially aimed to lower the technical barriers and provide theexploration power to address the requirements of experts, scientists and peoplein general who are willing to audit these technologies.Fil: Alemany, Laura Alonso. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Benotti, Luciana. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Gonzalez, Lucía. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Maina, Hernán Javier. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Busaniche, Beatriz. Fundación Via Libre; ArgentinaFil: Halvorsen, Alexia. Fundación Via Libre; ArgentinaFil: Bordone, Matías. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Sanchez, Jorge Adrian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaCornell University2022-07info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/211790Alemany, Laura Alonso; Benotti, Luciana; Gonzalez, Lucía; Maina, Hernán Javier; Busaniche, Beatriz; et al.; A tool to overcome technical barriers for bias assessment in human language technologies; Cornell University; arXiv; 2; 7-2022; 1-192331-8422CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/2207.06591v2info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:38:10Zoai:ri.conicet.gov.ar:11336/211790instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 09:38:10.681CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv A tool to overcome technical barriers for bias assessment in human language technologies
title A tool to overcome technical barriers for bias assessment in human language technologies
spellingShingle A tool to overcome technical barriers for bias assessment in human language technologies
Alemany, Laura Alonso
Natural Language Processing
Language Models
Bias
Stereotypes and Discrimination
title_short A tool to overcome technical barriers for bias assessment in human language technologies
title_full A tool to overcome technical barriers for bias assessment in human language technologies
title_fullStr A tool to overcome technical barriers for bias assessment in human language technologies
title_full_unstemmed A tool to overcome technical barriers for bias assessment in human language technologies
title_sort A tool to overcome technical barriers for bias assessment in human language technologies
dc.creator.none.fl_str_mv Alemany, Laura Alonso
Benotti, Luciana
Gonzalez, Lucía
Maina, Hernán Javier
Busaniche, Beatriz
Halvorsen, Alexia
Bordone, Matías
Sanchez, Jorge Adrian
author Alemany, Laura Alonso
author_facet Alemany, Laura Alonso
Benotti, Luciana
Gonzalez, Lucía
Maina, Hernán Javier
Busaniche, Beatriz
Halvorsen, Alexia
Bordone, Matías
Sanchez, Jorge Adrian
author_role author
author2 Benotti, Luciana
Gonzalez, Lucía
Maina, Hernán Javier
Busaniche, Beatriz
Halvorsen, Alexia
Bordone, Matías
Sanchez, Jorge Adrian
author2_role author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Natural Language Processing
Language Models
Bias
Stereotypes and Discrimination
topic Natural Language Processing
Language Models
Bias
Stereotypes and Discrimination
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Automatic processing of language is becoming pervasive in our lives, oftentaking central roles in our decision making, like choosing the wording for ourmessages and mails, translating our readings, or even having full conversationswith us. Word embeddings are a key component of modern natural languageprocessing systems. They provide a representation of words that has boosted theperformance of many applications, working as a semblance of meaning. Wordembeddings seem to capture a semblance of the meaning of words from raw text,but, at the same time, they also distill stereotypes and societal biases whichare subsequently relayed to the final applications. Such biases can bediscriminatory. It is very important to detect and mitigate those biases, toprevent discriminatory behaviors of automated processes, which can be much moreharmful than in the case of humans because their of their scale. There arecurrently many tools and techniques to detect and mitigate biases in wordembeddings, but they present many barriers for the engagement of people withouttechnical skills. As it happens, most of the experts in bias, either socialscientists or people with deep knowledge of the context where bias is harmful,do not have such skills, and they cannot engage in the processes of biasdetection because of the technical barriers. We have studied the barriers inexisting tools and have explored their possibilities and limitations withdifferent kinds of users. With this exploration, we propose to develop a toolthat is specially aimed to lower the technical barriers and provide theexploration power to address the requirements of experts, scientists and peoplein general who are willing to audit these technologies.
Fil: Alemany, Laura Alonso. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Benotti, Luciana. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Gonzalez, Lucía. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Maina, Hernán Javier. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Busaniche, Beatriz. Fundación Via Libre; Argentina
Fil: Halvorsen, Alexia. Fundación Via Libre; Argentina
Fil: Bordone, Matías. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Sanchez, Jorge Adrian. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
description Automatic processing of language is becoming pervasive in our lives, oftentaking central roles in our decision making, like choosing the wording for ourmessages and mails, translating our readings, or even having full conversationswith us. Word embeddings are a key component of modern natural languageprocessing systems. They provide a representation of words that has boosted theperformance of many applications, working as a semblance of meaning. Wordembeddings seem to capture a semblance of the meaning of words from raw text,but, at the same time, they also distill stereotypes and societal biases whichare subsequently relayed to the final applications. Such biases can bediscriminatory. It is very important to detect and mitigate those biases, toprevent discriminatory behaviors of automated processes, which can be much moreharmful than in the case of humans because their of their scale. There arecurrently many tools and techniques to detect and mitigate biases in wordembeddings, but they present many barriers for the engagement of people withouttechnical skills. As it happens, most of the experts in bias, either socialscientists or people with deep knowledge of the context where bias is harmful,do not have such skills, and they cannot engage in the processes of biasdetection because of the technical barriers. We have studied the barriers inexisting tools and have explored their possibilities and limitations withdifferent kinds of users. With this exploration, we propose to develop a toolthat is specially aimed to lower the technical barriers and provide theexploration power to address the requirements of experts, scientists and peoplein general who are willing to audit these technologies.
publishDate 2022
dc.date.none.fl_str_mv 2022-07
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/211790
Alemany, Laura Alonso; Benotti, Luciana; Gonzalez, Lucía; Maina, Hernán Javier; Busaniche, Beatriz; et al.; A tool to overcome technical barriers for bias assessment in human language technologies; Cornell University; arXiv; 2; 7-2022; 1-19
2331-8422
CONICET Digital
CONICET
url http://hdl.handle.net/11336/211790
identifier_str_mv Alemany, Laura Alonso; Benotti, Luciana; Gonzalez, Lucía; Maina, Hernán Javier; Busaniche, Beatriz; et al.; A tool to overcome technical barriers for bias assessment in human language technologies; Cornell University; arXiv; 2; 7-2022; 1-19
2331-8422
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/2207.06591v2
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Cornell University
publisher.none.fl_str_mv Cornell University
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613206319824896
score 13.070432