Challenging machine translation engines: Some Spanish-English linguistic problems put to the test

This work is an evaluation of machine translation engines completed in 2018 and 2021, inspired by Isabelle, Cherry & Foster (2017), and Isabelle & Kuhn (2018). The challenge consisted of testing MTs Google Translate and Bing and DeepL in the translation of certain linguistic problems...

Descripción completa

Detalles Bibliográficos
Autor: Peña Aguilar, Argelia
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:Brasil
Institución:Universidade Federal de Santa Catarina (UFSC)
Repositorio:Cadernos de Tradução (Florianópolis. Online)
Idioma:inglés
OAI Identifier:oai:periodicos.ufsc.br:article/85397
Acceso en línea:https://periodicos.ufsc.br/index.php/traducao/article/view/85397
Access Level:acceso abierto
Palabra clave:Machine Translation
Pre-Editing
Post-Editing
Google Translate
Bing
DeepL
id BR_0540bb3d97df951db2e05fa960598c21
oai_identifier_str oai:periodicos.ufsc.br:article/85397
network_acronym_str BR
network_name_str Brasil
repository_id_str
spelling Challenging machine translation engines: Some Spanish-English linguistic problems put to the testMachine TranslationPre-EditingPost-EditingGoogle TranslateBingDeepLThis work is an evaluation of machine translation engines completed in 2018 and 2021, inspired by Isabelle, Cherry & Foster (2017), and Isabelle & Kuhn (2018). The challenge consisted of testing MTs Google Translate and Bing and DeepL in the translation of certain linguistic problems normally found when translating from Spanish into English. The divergences representing a “challenge” to the engines were of morphological and lexical-syntactical types. The absolute winner of the challenge was DeepL, in second place was Bing from Microsoft, and Google was the engine that was the poorest in the management of the linguistic problems. In terms of time, when comparing the engines three years apart, it was found that DeepL was the only one that enhanced its performance by correcting a problem it had before in a test sentence. This was not the case for the other two, on the contrary, their translations were of lower quality. These machines do not seem to be consistent in the manner in which they are improved. These findings may be valuable for translators who may work with these systems as pre or post-editors so that their efforts may be better directed.Universidade Federal de Santa Catarina2023-12-29info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.ufsc.br/index.php/traducao/article/view/8539710.5007/2175-7968.2023.e85397Cadernos de Tradução; Vol. 43 No. 1 (2023): Edição Regular (Fluxo Contínuo); 1-26Cadernos de Tradução; Vol. 43 Núm. 1 (2023): Edição Regular (Fluxo Contínuo); 1-26Cadernos de Tradução; v. 43 n. 1 (2023): Edição Regular (Fluxo Contínuo); 1-262175-79681414-526Xreponame:Cadernos de Tradução (Florianópolis. Online)instname:Universidade Federal de Santa Catarina (UFSC)instacron:UFSCenghttps://periodicos.ufsc.br/index.php/traducao/article/view/85397/52725Copyright (c) 2023 Cadernos de Traduçãohttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessPeña Aguilar, Argelia2025-02-12T10:11:10Zoai:periodicos.ufsc.br:article/85397Revistahttps://periodicos.ufsc.br/index.php/traducao/indexPUBhttps://periodicos.ufsc.br/index.php/traducao/oaieditorcadernostraducao@contato.ufsc.br||ecadernos@gmail.com||editorcadernostraducao@contato.ufsc.br|| cadernostraducao@contato.ufsc.br2175-79681414-526Xopendoar:2025-02-12T10:11:10Cadernos de Tradução (Florianópolis. Online) - Universidade Federal de Santa Catarina (UFSC)false
dc.title.none.fl_str_mv Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
title Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
spellingShingle Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
Peña Aguilar, Argelia
Machine Translation
Pre-Editing
Post-Editing
Google Translate
Bing
DeepL
title_short Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
title_full Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
title_fullStr Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
title_full_unstemmed Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
title_sort Challenging machine translation engines: Some Spanish-English linguistic problems put to the test
dc.creator.none.fl_str_mv Peña Aguilar, Argelia
author Peña Aguilar, Argelia
author_facet Peña Aguilar, Argelia
author_role author
dc.subject.por.fl_str_mv Machine Translation
Pre-Editing
Post-Editing
Google Translate
Bing
DeepL
topic Machine Translation
Pre-Editing
Post-Editing
Google Translate
Bing
DeepL
description This work is an evaluation of machine translation engines completed in 2018 and 2021, inspired by Isabelle, Cherry & Foster (2017), and Isabelle & Kuhn (2018). The challenge consisted of testing MTs Google Translate and Bing and DeepL in the translation of certain linguistic problems normally found when translating from Spanish into English. The divergences representing a “challenge” to the engines were of morphological and lexical-syntactical types. The absolute winner of the challenge was DeepL, in second place was Bing from Microsoft, and Google was the engine that was the poorest in the management of the linguistic problems. In terms of time, when comparing the engines three years apart, it was found that DeepL was the only one that enhanced its performance by correcting a problem it had before in a test sentence. This was not the case for the other two, on the contrary, their translations were of lower quality. These machines do not seem to be consistent in the manner in which they are improved. These findings may be valuable for translators who may work with these systems as pre or post-editors so that their efforts may be better directed.
publishDate 2023
dc.date.none.fl_str_mv 2023-12-29
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://periodicos.ufsc.br/index.php/traducao/article/view/85397
10.5007/2175-7968.2023.e85397
url https://periodicos.ufsc.br/index.php/traducao/article/view/85397
identifier_str_mv 10.5007/2175-7968.2023.e85397
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://periodicos.ufsc.br/index.php/traducao/article/view/85397/52725
dc.rights.driver.fl_str_mv Copyright (c) 2023 Cadernos de Tradução
https://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2023 Cadernos de Tradução
https://creativecommons.org/licenses/by/4.0
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade Federal de Santa Catarina
publisher.none.fl_str_mv Universidade Federal de Santa Catarina
dc.source.none.fl_str_mv Cadernos de Tradução; Vol. 43 No. 1 (2023): Edição Regular (Fluxo Contínuo); 1-26
Cadernos de Tradução; Vol. 43 Núm. 1 (2023): Edição Regular (Fluxo Contínuo); 1-26
Cadernos de Tradução; v. 43 n. 1 (2023): Edição Regular (Fluxo Contínuo); 1-26
2175-7968
1414-526X
reponame:Cadernos de Tradução (Florianópolis. Online)
instname:Universidade Federal de Santa Catarina (UFSC)
instacron:UFSC
instname_str Universidade Federal de Santa Catarina (UFSC)
instacron_str UFSC
institution UFSC
reponame_str Cadernos de Tradução (Florianópolis. Online)
collection Cadernos de Tradução (Florianópolis. Online)
repository.name.fl_str_mv Cadernos de Tradução (Florianópolis. Online) - Universidade Federal de Santa Catarina (UFSC)
repository.mail.fl_str_mv editorcadernostraducao@contato.ufsc.br||ecadernos@gmail.com||editorcadernostraducao@contato.ufsc.br|| cadernostraducao@contato.ufsc.br
_version_ 1853676134348095488
score 15.300719

Similares en LA Referencia