Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge

Neural Machine Translation has the power of learning from a large collection of data, which allows it to learn translations effectively and without requiring linguistic knowledge from the languages to translate. The main drawback is that this large collection of data may not exist (i.e. low resource...

ver descrição completa

Detalhes bibliográficos
Autor: Kharitonova, Ksenia
Formato: tesis de maestría
Fecha de publicación:2021
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/348437
Acesso em linha:https://hdl.handle.net/2117/348437
Access Level:acceso abierto
Palavra-chave:Machine translating
gender bias
transformer
factored transformer
linguistic input
machine translation
linguistic information
factored machine translation
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_31e9efa7b678039c4e570680466cb3fb
oai_identifier_str oai:upcommons.upc.edu:2117/348437
network_acronym_str ES
network_name_str España
repository_id_str
spelling Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledgeKharitonova, KseniaMachine translatinggender biastransformerfactored transformerlinguistic inputmachine translationlinguistic informationfactored machine translationTraducció automàticaÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialNeural Machine Translation has the power of learning from a large collection of data, which allows it to learn translations effectively and without requiring linguistic knowledge from the languages to translate. The main drawback is that this large collection of data may not exist (i.e. low resourced languages) or this data reproduces the social biases existing in the society. While introducing linguistic knowledge has been widely studied to reduce the impact of lack of data, it may also be interesting to use it as a potential tool to mitigate and neutralize biases. This project explores the Factored Transformer which is a neural machine translation architecture which allows for introducing linguistic features and its impact in gender bias mitigation. In order to study the gender bias in the results of machine translation models, we use the standard WinoMT framework by Stanovsky et al. (2019) that permits to detect gender bias in the translations from English to languages with grammatical gender. We investigate the influence of adding linguistic factors to Factored Transformer on 4 language pairs: English-French, English- Spanish, English-German and English-Russian and detect improvements using several types of linguistic input. Besides general gender bias metrics, we use the methodology described in Costa-jussà et al. (2020) for the interpretability analysis of contextual source embeddings and encoder-decoder attention.Universitat Politècnica de CatalunyaRuiz Costa-Jussà, Marta20212021-04-2920212021-07-05master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/348437reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3484372026-05-27T15:37:01Z
dc.title.none.fl_str_mv Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
title Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
spellingShingle Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
Kharitonova, Ksenia
Machine translating
gender bias
transformer
factored transformer
linguistic input
machine translation
linguistic information
factored machine translation
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
title_full Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
title_fullStr Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
title_full_unstemmed Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
title_sort Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
dc.creator.none.fl_str_mv Kharitonova, Ksenia
author Kharitonova, Ksenia
author_facet Kharitonova, Ksenia
author_role author
dc.contributor.none.fl_str_mv Ruiz Costa-Jussà, Marta
dc.subject.none.fl_str_mv Machine translating
gender bias
transformer
factored transformer
linguistic input
machine translation
linguistic information
factored machine translation
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Machine translating
gender bias
transformer
factored transformer
linguistic input
machine translation
linguistic information
factored machine translation
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description Neural Machine Translation has the power of learning from a large collection of data, which allows it to learn translations effectively and without requiring linguistic knowledge from the languages to translate. The main drawback is that this large collection of data may not exist (i.e. low resourced languages) or this data reproduces the social biases existing in the society. While introducing linguistic knowledge has been widely studied to reduce the impact of lack of data, it may also be interesting to use it as a potential tool to mitigate and neutralize biases. This project explores the Factored Transformer which is a neural machine translation architecture which allows for introducing linguistic features and its impact in gender bias mitigation. In order to study the gender bias in the results of machine translation models, we use the standard WinoMT framework by Stanovsky et al. (2019) that permits to detect gender bias in the translations from English to languages with grammatical gender. We investigate the influence of adding linguistic factors to Factored Transformer on 4 language pairs: English-French, English- Spanish, English-German and English-Russian and detect improvements using several types of linguistic input. Besides general gender bias metrics, we use the methodology described in Costa-jussà et al. (2020) for the interpretability analysis of contextual source embeddings and encoder-decoder attention.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-04-29
2021
2021-07-05
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/348437
url https://hdl.handle.net/2117/348437
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
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
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405641518350336
score 15,301629

Registos relacionados