Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs

This study aims to investigate the effect of data augmentation through translation memories for desktop machine translation (MT) fine-tuning in OPUS-CAT. It also focuses on assessing the usefulness of desktop MT for professional translators. Engines in three language pairs (English → Turkish, Englis...

Descripción completa

Detalles Bibliográficos
Autores: Dogru, Gokhan, Moorkens, Joss
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/69349
Acceso en línea:http://hdl.handle.net/10230/69349
http://dx.doi.org/10.26034/cm.jostrans.2024.4716
Access Level:acceso abierto
Palabra clave:Machine translation fine-tuning
Domain adaptation
Desktop machine translation
Localization
Parallel corpora
Professional translators
Machine translation evaluation
id ES_9b4f3d862ed2f0dfb717c9366393f41b
oai_identifier_str oai:repositori.upf.edu:10230/69349
network_acronym_str ES
network_name_str España
repository_id_str
spelling Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairsDogru, GokhanMoorkens, JossMachine translation fine-tuningDomain adaptationDesktop machine translationLocalizationParallel corporaProfessional translatorsMachine translation evaluationThis study aims to investigate the effect of data augmentation through translation memories for desktop machine translation (MT) fine-tuning in OPUS-CAT. It also focuses on assessing the usefulness of desktop MT for professional translators. Engines in three language pairs (English → Turkish, English → Spanish, and English → Catalan) are fine-tuned with corpora of two different sizes. The translation quality of each engine is measured through automatic evaluation metrics (BLEU, chrF2, TER and COMET) and human evaluation metrics (ranking, adequacy and fluency). Overall evaluation results indicate promising quality improvements in all three language pairs and imply that the use of desktop MT applications such as OPUS-CAT and fine-tuning MT engines with custom data in a translator’s desktop can potentially provide high-quality translations aside from their advantages such as privacy, confidentiality and low use of computation power.Jostrans (Journal of Specialised Translation)202520252024info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/69349http://dx.doi.org/10.26034/cm.jostrans.2024.4716reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésThe Journal of Specialised Translation. 2024;41:149–78This work is licensed under a Creative Commons Attribution 4.0 International License.http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/693492026-06-12T07:21:37Z
dc.title.none.fl_str_mv Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
title Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
spellingShingle Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
Dogru, Gokhan
Machine translation fine-tuning
Domain adaptation
Desktop machine translation
Localization
Parallel corpora
Professional translators
Machine translation evaluation
title_short Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
title_full Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
title_fullStr Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
title_full_unstemmed Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
title_sort Data augmentation with translation memories for desktop machine translation fine-tuning in 3 language pairs
dc.creator.none.fl_str_mv Dogru, Gokhan
Moorkens, Joss
author Dogru, Gokhan
author_facet Dogru, Gokhan
Moorkens, Joss
author_role author
author2 Moorkens, Joss
author2_role author
dc.subject.none.fl_str_mv Machine translation fine-tuning
Domain adaptation
Desktop machine translation
Localization
Parallel corpora
Professional translators
Machine translation evaluation
topic Machine translation fine-tuning
Domain adaptation
Desktop machine translation
Localization
Parallel corpora
Professional translators
Machine translation evaluation
description This study aims to investigate the effect of data augmentation through translation memories for desktop machine translation (MT) fine-tuning in OPUS-CAT. It also focuses on assessing the usefulness of desktop MT for professional translators. Engines in three language pairs (English → Turkish, English → Spanish, and English → Catalan) are fine-tuned with corpora of two different sizes. The translation quality of each engine is measured through automatic evaluation metrics (BLEU, chrF2, TER and COMET) and human evaluation metrics (ranking, adequacy and fluency). Overall evaluation results indicate promising quality improvements in all three language pairs and imply that the use of desktop MT applications such as OPUS-CAT and fine-tuning MT engines with custom data in a translator’s desktop can potentially provide high-quality translations aside from their advantages such as privacy, confidentiality and low use of computation power.
publishDate 2024
dc.date.none.fl_str_mv 2024
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/69349
http://dx.doi.org/10.26034/cm.jostrans.2024.4716
url http://hdl.handle.net/10230/69349
http://dx.doi.org/10.26034/cm.jostrans.2024.4716
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv The Journal of Specialised Translation. 2024;41:149–78
dc.rights.none.fl_str_mv This work is licensed under a Creative Commons Attribution 4.0 International License.
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv This work is licensed under a Creative Commons Attribution 4.0 International License.
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Jostrans (Journal of Specialised Translation)
publisher.none.fl_str_mv Jostrans (Journal of Specialised Translation)
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869414494112841728
score 15.81155

Similares en LA Referencia