Gender Bias and Contextual Sensitivity in Machine Translation

Turkish, a language that does not explicitly mark gender in pronouns, poses a unique challenge for machine translation systems, particularly in cases of gender-neutral or ambiguous context. This study investigates the performance of neural machine translation (NMT) and large language models (LLMs) i...

Descripción completa

Detalles Bibliográficos
Autores: Portillo Palma, Seyda|||0000-0001-6986-231X, Alvarez-Vidal, Sergi|||0000-0002-6355-4559
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:318830
Acceso en línea:https://ddd.uab.cat/record/318830
https://dx.doi.org/urn:doi:10.29228/transLogos.67
Access Level:acceso abierto
Palabra clave:Gender bias
Emotion translation
Machine translation
Context awareness
Anaphora resolution
id ES_95dc778fbcd7062d7998bb2c7fdc2ae8
oai_identifier_str oai:ddd.uab.cat:318830
network_acronym_str ES
network_name_str España
repository_id_str
spelling Gender Bias and Contextual Sensitivity in Machine TranslationA Focus on Turkish Subject-Dropped SentencesPortillo Palma, Seyda|||0000-0001-6986-231XAlvarez-Vidal, Sergi|||0000-0002-6355-4559Gender biasEmotion translationMachine translationContext awarenessAnaphora resolutionTurkish, a language that does not explicitly mark gender in pronouns, poses a unique challenge for machine translation systems, particularly in cases of gender-neutral or ambiguous context. This study investigates the performance of neural machine translation (NMT) and large language models (LLMs) in resolving gender ambiguity when translating Turkish subject-dropped sentences into English. The analysis examines four prominent models-Google Translate, DeepL, ChatGPT, and Gemini-evaluating their pronoun selection and the extent of gender bias, especially in emotionally charged or contextually nuanced sentences. A primarily quantitative evaluation reveals a persistent gender bias across all models, with LLMs demonstrating relatively better performance than NMTs when clearer contextual information is present. However, all models exhibit limitations in managing the complexities of cross-linguistic gender representation. This research highlights the pressing need for gender-neutral solutions and advancements in context-sensitive translation. Furthermore, we introduce a moderately sized annotated Turkish corpus, designed to facilitate future studies on gender ambiguity in machine translation (MT). This dataset provides a valuable resource for enhancing the accuracy of gendered pronoun resolution and fostering more inclusive, bias-reduced translation systems. Overall, the study contributes to the growing discourse on reducing bias in language models while addressing the challenges of nuanced linguistic diversity in translation. 22024-01-0120242024-01-01Articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://ddd.uab.cat/record/318830https://dx.doi.org/urn:doi:10.29228/transLogos.67reponame:Dipòsit Digital de Documents de la UABinstname:Universitat Autònoma de BarcelonaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.https://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ddd.uab.cat:3188302026-06-06T12:50:31Z
dc.title.none.fl_str_mv Gender Bias and Contextual Sensitivity in Machine Translation
A Focus on Turkish Subject-Dropped Sentences
title Gender Bias and Contextual Sensitivity in Machine Translation
spellingShingle Gender Bias and Contextual Sensitivity in Machine Translation
Portillo Palma, Seyda|||0000-0001-6986-231X
Gender bias
Emotion translation
Machine translation
Context awareness
Anaphora resolution
title_short Gender Bias and Contextual Sensitivity in Machine Translation
title_full Gender Bias and Contextual Sensitivity in Machine Translation
title_fullStr Gender Bias and Contextual Sensitivity in Machine Translation
title_full_unstemmed Gender Bias and Contextual Sensitivity in Machine Translation
title_sort Gender Bias and Contextual Sensitivity in Machine Translation
dc.creator.none.fl_str_mv Portillo Palma, Seyda|||0000-0001-6986-231X
Alvarez-Vidal, Sergi|||0000-0002-6355-4559
author Portillo Palma, Seyda|||0000-0001-6986-231X
author_facet Portillo Palma, Seyda|||0000-0001-6986-231X
Alvarez-Vidal, Sergi|||0000-0002-6355-4559
author_role author
author2 Alvarez-Vidal, Sergi|||0000-0002-6355-4559
author2_role author
dc.subject.none.fl_str_mv Gender bias
Emotion translation
Machine translation
Context awareness
Anaphora resolution
topic Gender bias
Emotion translation
Machine translation
Context awareness
Anaphora resolution
description Turkish, a language that does not explicitly mark gender in pronouns, poses a unique challenge for machine translation systems, particularly in cases of gender-neutral or ambiguous context. This study investigates the performance of neural machine translation (NMT) and large language models (LLMs) in resolving gender ambiguity when translating Turkish subject-dropped sentences into English. The analysis examines four prominent models-Google Translate, DeepL, ChatGPT, and Gemini-evaluating their pronoun selection and the extent of gender bias, especially in emotionally charged or contextually nuanced sentences. A primarily quantitative evaluation reveals a persistent gender bias across all models, with LLMs demonstrating relatively better performance than NMTs when clearer contextual information is present. However, all models exhibit limitations in managing the complexities of cross-linguistic gender representation. This research highlights the pressing need for gender-neutral solutions and advancements in context-sensitive translation. Furthermore, we introduce a moderately sized annotated Turkish corpus, designed to facilitate future studies on gender ambiguity in machine translation (MT). This dataset provides a valuable resource for enhancing the accuracy of gendered pronoun resolution and fostering more inclusive, bias-reduced translation systems. Overall, the study contributes to the growing discourse on reducing bias in language models while addressing the challenges of nuanced linguistic diversity in translation.
publishDate 2024
dc.date.none.fl_str_mv 2
2024-01-01
2024
2024-01-01
dc.type.none.fl_str_mv Article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://ddd.uab.cat/record/318830
https://dx.doi.org/urn:doi:10.29228/transLogos.67
url https://ddd.uab.cat/record/318830
https://dx.doi.org/urn:doi:10.29228/transLogos.67
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Dipòsit Digital de Documents de la UAB
instname:Universitat Autònoma de Barcelona
instname_str Universitat Autònoma de Barcelona
reponame_str Dipòsit Digital de Documents de la UAB
collection Dipòsit Digital de Documents de la UAB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869413888028573696
score 15,811543

Similares en LA Referencia