Large Language Models for Interactive Machine Translation

[EN] Machine translation is an ever-evolving field and is attached to continuous improvement. Consequently, the results that it offers are far from being perfect but are obtained really fast. In practical applications, the translations obtained automatically need to be revised by a human translator....

Descripción completa

Detalles Bibliográficos
Autores: Gómez-González, Sergio|||0009-0006-0061-8056, Domingo-Ballester, Miguel|||0000-0002-7910-4536, Navarro-Martínez, Ángel|||0000-0002-5957-8152, Casacuberta Nolla, Francisco|||0000-0002-8497-5598
Tipo de recurso: artículo
Fecha de publicación:2026
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:dnet:riunet______::772ac765f9d8059a29902d5561b5a9db
Acceso en línea:https://riunet.upv.es/handle/10251/234981
Access Level:acceso embargado
Palabra clave:Language model
Machine translation
Interactive machine translation
Segment-based interactive machine translation
Restricted generation
id ES_f442c026bf119f2a2d621eaab2eed3a3
oai_identifier_str oai:dnet:riunet______::772ac765f9d8059a29902d5561b5a9db
network_acronym_str ES
network_name_str España
repository_id_str
spelling Large Language Models for Interactive Machine TranslationGómez-González, Sergio|||0009-0006-0061-8056Domingo-Ballester, Miguel|||0000-0002-7910-4536Navarro-Martínez, Ángel|||0000-0002-5957-8152Casacuberta Nolla, Francisco|||0000-0002-8497-5598Language modelMachine translationInteractive machine translationSegment-based interactive machine translationRestricted generation[EN] Machine translation is an ever-evolving field and is attached to continuous improvement. Consequently, the results that it offers are far from being perfect but are obtained really fast. In practical applications, the translations obtained automatically need to be revised by a human translator. On the other hand, the translations performed completely by humans have a high quality but take much time. Interactive Machine Translation (IMT) has been one of the most promising approaches to improve the quality of the translation while minimizing the user effort and time needed. Last advances in natural language processing have involved Large Language Models (LLM) with great success. In this work we integrate LLMs into two IMT interaction protocols: prefix-based and segment-based. We have performed a comparative study with four different multilingual LLMs for the IMT task in a renowned dataset for both IMT protocols. The systems that we propose effectively reduce the post-editing effort for the prefix-based approach.This work received funding from ValgrAI (Valencian Graduate School and Research Network for Artificial Intelligence), Generalitat Valencia, European NextGenerationEU/PRTR under project FAKEnHATE-PdC (PDC2022-133118-I00).Springer-VerlagDepartamento de Sistemas Informáticos y ComputaciónEscuela Técnica Superior de Ingeniería Geodésica, Cartográfica y TopográficaEscuela Técnica Superior de Ingeniería InformáticaCentro de Investigación Pattern Recognition and Human Language TechnologyAgencia Estatal de InvestigaciónValencian Graduate School and Research Network of Artificial IntelligenceRepositorio Institucional de la Universitat Politècnica de València Riunet20262026-01-0120262026-05-0820262026-07-29journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://riunet.upv.es/handle/10251/234981reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PDC2022-133118-I00 DESINFORMACION Y DISCURSO DE ODIOembargoed accesshttp://purl.org/coar/access_right/c_f1cfReserva de todos los derechoshttp://rightsstatements.org/vocab/InC/1.0/info:eu-repo/semantics/embargoedAccessoai:dnet:riunet______::772ac765f9d8059a29902d5561b5a9db2026-06-13T07:49:27Z
dc.title.none.fl_str_mv Large Language Models for Interactive Machine Translation
title Large Language Models for Interactive Machine Translation
spellingShingle Large Language Models for Interactive Machine Translation
Gómez-González, Sergio|||0009-0006-0061-8056
Language model
Machine translation
Interactive machine translation
Segment-based interactive machine translation
Restricted generation
title_short Large Language Models for Interactive Machine Translation
title_full Large Language Models for Interactive Machine Translation
title_fullStr Large Language Models for Interactive Machine Translation
title_full_unstemmed Large Language Models for Interactive Machine Translation
title_sort Large Language Models for Interactive Machine Translation
dc.creator.none.fl_str_mv Gómez-González, Sergio|||0009-0006-0061-8056
Domingo-Ballester, Miguel|||0000-0002-7910-4536
Navarro-Martínez, Ángel|||0000-0002-5957-8152
Casacuberta Nolla, Francisco|||0000-0002-8497-5598
author Gómez-González, Sergio|||0009-0006-0061-8056
author_facet Gómez-González, Sergio|||0009-0006-0061-8056
Domingo-Ballester, Miguel|||0000-0002-7910-4536
Navarro-Martínez, Ángel|||0000-0002-5957-8152
Casacuberta Nolla, Francisco|||0000-0002-8497-5598
author_role author
author2 Domingo-Ballester, Miguel|||0000-0002-7910-4536
Navarro-Martínez, Ángel|||0000-0002-5957-8152
Casacuberta Nolla, Francisco|||0000-0002-8497-5598
author2_role author
author
author
dc.contributor.none.fl_str_mv Departamento de Sistemas Informáticos y Computación
Escuela Técnica Superior de Ingeniería Geodésica, Cartográfica y Topográfica
Escuela Técnica Superior de Ingeniería Informática
Centro de Investigación Pattern Recognition and Human Language Technology
Agencia Estatal de Investigación
Valencian Graduate School and Research Network of Artificial Intelligence
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Language model
Machine translation
Interactive machine translation
Segment-based interactive machine translation
Restricted generation
topic Language model
Machine translation
Interactive machine translation
Segment-based interactive machine translation
Restricted generation
description [EN] Machine translation is an ever-evolving field and is attached to continuous improvement. Consequently, the results that it offers are far from being perfect but are obtained really fast. In practical applications, the translations obtained automatically need to be revised by a human translator. On the other hand, the translations performed completely by humans have a high quality but take much time. Interactive Machine Translation (IMT) has been one of the most promising approaches to improve the quality of the translation while minimizing the user effort and time needed. Last advances in natural language processing have involved Large Language Models (LLM) with great success. In this work we integrate LLMs into two IMT interaction protocols: prefix-based and segment-based. We have performed a comparative study with four different multilingual LLMs for the IMT task in a renowned dataset for both IMT protocols. The systems that we propose effectively reduce the post-editing effort for the prefix-based approach.
publishDate 2026
dc.date.none.fl_str_mv 2026
2026-01-01
2026
2026-05-08
2026
2026-07-29
dc.type.none.fl_str_mv journal 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://riunet.upv.es/handle/10251/234981
url https://riunet.upv.es/handle/10251/234981
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PDC2022-133118-I00 DESINFORMACION Y DISCURSO DE ODIO
dc.rights.none.fl_str_mv embargoed access
http://purl.org/coar/access_right/c_f1cf
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/embargoedAccess
rights_invalid_str_mv embargoed access
http://purl.org/coar/access_right/c_f1cf
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer-Verlag
publisher.none.fl_str_mv Springer-Verlag
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869424455684456448
score 15.812429

Similares en LA Referencia