Improving multilingual NMT by projecting language representations

Machine Translation (MT), is one of the most important tasks related to natural language processing which facilitates seamless communication across different languages by automating the translation process, thereby significantly reducing communication costs. In this context, a multilingual neural ma...

ver descrição completa

Detalhes bibliográficos
Autor: García Gilabert, Javier
Tipo de documento: dissertação
Data de publicação:2024
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/416255
Acesso em linha:https://hdl.handle.net/2117/416255
Access Level:Acceso aberto
Palavra-chave:Machine translating
Artificial intelligence
traducció automàtica
representacions agnòstiques
machine translation
agnostic representations
Traducció automàtica
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_ffd8ab083faa0599085b51205b2779ff
oai_identifier_str oai:upcommons.upc.edu:2117/416255
network_acronym_str ES
network_name_str España
repository_id_str
spelling Improving multilingual NMT by projecting language representationsGarcía Gilabert, JavierMachine translatingArtificial intelligencetraducció automàticarepresentacions agnòstiquesmachine translationagnostic representationsTraducció automàticaIntel·ligència artificialÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialMachine Translation (MT), is one of the most important tasks related to natural language processing which facilitates seamless communication across different languages by automating the translation process, thereby significantly reducing communication costs. In this context, a multilingual neural machine translation (MNMT) system emerges as a cost-effective solution, capable of handling translations across multiple language pairs. An interesting property of MNMT systems is their ability to perform zero-shot translation, where the model translates between language pairs it has not explicitly seen before. This feature is particularly promising as it could potentially reduce the extensive resources and parameters typically required for MNMT models. Traditionally, MNMT models were thought to utilize a representation space independent of any specific language. This interlingua representation would allow the model to encode phrases conveying the same meaning similarly, regardless of the language, thereby aiding the translation process. However, in practice, it has been shown that this interlingua representation space is not as robust as previously assumed. In this project, we aim to study how MNMT representations still exhibit language dependent information and devise techniques to improve the model's representation. To achieve this goal, we propose some methods based on language projections.Universitat Politècnica de CatalunyaEscolano Peinado, CarlosRodríguez Fonollosa, José Adrián20242024-06-2720242024-10-18master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/416255reponame: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:2117/4162552026-05-27T15:37:01Z
dc.title.none.fl_str_mv Improving multilingual NMT by projecting language representations
title Improving multilingual NMT by projecting language representations
spellingShingle Improving multilingual NMT by projecting language representations
García Gilabert, Javier
Machine translating
Artificial intelligence
traducció automàtica
representacions agnòstiques
machine translation
agnostic representations
Traducció automàtica
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Improving multilingual NMT by projecting language representations
title_full Improving multilingual NMT by projecting language representations
title_fullStr Improving multilingual NMT by projecting language representations
title_full_unstemmed Improving multilingual NMT by projecting language representations
title_sort Improving multilingual NMT by projecting language representations
dc.creator.none.fl_str_mv García Gilabert, Javier
author García Gilabert, Javier
author_facet García Gilabert, Javier
author_role author
dc.contributor.none.fl_str_mv Escolano Peinado, Carlos
Rodríguez Fonollosa, José Adrián
dc.subject.none.fl_str_mv Machine translating
Artificial intelligence
traducció automàtica
representacions agnòstiques
machine translation
agnostic representations
Traducció automàtica
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Machine translating
Artificial intelligence
traducció automàtica
representacions agnòstiques
machine translation
agnostic representations
Traducció automàtica
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description Machine Translation (MT), is one of the most important tasks related to natural language processing which facilitates seamless communication across different languages by automating the translation process, thereby significantly reducing communication costs. In this context, a multilingual neural machine translation (MNMT) system emerges as a cost-effective solution, capable of handling translations across multiple language pairs. An interesting property of MNMT systems is their ability to perform zero-shot translation, where the model translates between language pairs it has not explicitly seen before. This feature is particularly promising as it could potentially reduce the extensive resources and parameters typically required for MNMT models. Traditionally, MNMT models were thought to utilize a representation space independent of any specific language. This interlingua representation would allow the model to encode phrases conveying the same meaning similarly, regardless of the language, thereby aiding the translation process. However, in practice, it has been shown that this interlingua representation space is not as robust as previously assumed. In this project, we aim to study how MNMT representations still exhibit language dependent information and devise techniques to improve the model's representation. To achieve this goal, we propose some methods based on language projections.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-06-27
2024
2024-10-18
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/2117/416255
url https://hdl.handle.net/2117/416255
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_ 1869425811379978240
score 15,812455

Registros relacionados