Linguistic knowledge-based vocabularies for Neural Machine Translation

This article has been published in a revised form in Natural Language Engineering https://doi.org/10.1017/S1351324920000364. This version is free to view and download for private research and study only. Not for re-distribution, re-sale or use in derivative works. © Cambridge University Press

Detalles Bibliográficos
Autores: Casas Manzanares, Noé, Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X, Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939, Alonso, Juan, Fanlo, Ramon
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/330835
Acceso en línea:https://hdl.handle.net/2117/330835
https://dx.doi.org/10.1017/S1351324920000364
Access Level:acceso abierto
Palabra clave:Machine translating
Machine translation
Neural network
Morphology
Vocabulary
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_2e9963c2c482ca3e4d890d151d33ff4f
oai_identifier_str oai:upcommons.upc.edu:2117/330835
network_acronym_str ES
network_name_str España
repository_id_str
spelling Linguistic knowledge-based vocabularies for Neural Machine TranslationCasas Manzanares, NoéRuiz Costa-Jussà, Marta|||0000-0002-5703-520XRodríguez Fonollosa, José Adrián|||0000-0001-9513-7939Alonso, JuanFanlo, RamonMachine translatingMachine translationNeural networkMorphologyVocabularyTraducció automàticaÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialThis article has been published in a revised form in Natural Language Engineering https://doi.org/10.1017/S1351324920000364. This version is free to view and download for private research and study only. Not for re-distribution, re-sale or use in derivative works. © Cambridge University PressNeural Networks applied to Machine Translation need a finite vocabulary to express textual information as a sequence of discrete tokens. The currently dominant subword vocabularies exploit statistically-discovered common parts of words to achieve the flexibility of character-based vocabularies without delegating the whole learning of word formation to the neural network. However, they trade this for the inability to apply word-level token associations, which limits their use in semantically-rich areas and prevents some transfer learning approaches e.g. cross-lingual pretrained embeddings, and reduces their interpretability. In this work, we propose new hybrid linguistically-grounded vocabulary definition strategies that keep both the advantages of subword vocabularies and the word-level associations, enabling neural networks to profit from the derived benefits. We test the proposed approaches in both morphologically rich and poor languages, showing that, for the former, the quality in the translation of out-of-domain texts is improved with respect to a strong subword baseline.This work is partially supported by Lucy Software / United Language Group (ULG) and the Catalan Agency for Management of University and Research Grants (AGAUR) through an Industrial PhD Grant. This work is also supported in part by the Spanish Ministerio de Economa y Competitividad, the European Regional Development Fund and the Agencia Estatal de Investigacin, through the postdoctoral senior grant Ramn y Cajal, contract TEC2015-69266-P (MINECO/FEDER,EU) and contract PCIN-2017-079 (AEI/MINECO).Peer ReviewedCambridge University Press20202020-01-0120202020-10-26journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://hdl.handle.net/2117/330835https://dx.doi.org/10.1017/S1351324920000364reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengMinisterio de Economía y Competitividad http://doi.org/10.13039/501100003329 TEC2015-69266-P TECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ Y AUDIOAgencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación (PEICTI) 2013-2016 PCIN-2017-079 AUTONOMOUS LIFELONG LEARNING INTELLIGENT SYSTEMSopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3308352026-05-27T15:37:01Z
dc.title.none.fl_str_mv Linguistic knowledge-based vocabularies for Neural Machine Translation
title Linguistic knowledge-based vocabularies for Neural Machine Translation
spellingShingle Linguistic knowledge-based vocabularies for Neural Machine Translation
Casas Manzanares, Noé
Machine translating
Machine translation
Neural network
Morphology
Vocabulary
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Linguistic knowledge-based vocabularies for Neural Machine Translation
title_full Linguistic knowledge-based vocabularies for Neural Machine Translation
title_fullStr Linguistic knowledge-based vocabularies for Neural Machine Translation
title_full_unstemmed Linguistic knowledge-based vocabularies for Neural Machine Translation
title_sort Linguistic knowledge-based vocabularies for Neural Machine Translation
dc.creator.none.fl_str_mv Casas Manzanares, Noé
Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X
Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939
Alonso, Juan
Fanlo, Ramon
author Casas Manzanares, Noé
author_facet Casas Manzanares, Noé
Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X
Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939
Alonso, Juan
Fanlo, Ramon
author_role author
author2 Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X
Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939
Alonso, Juan
Fanlo, Ramon
author2_role author
author
author
author
dc.subject.none.fl_str_mv Machine translating
Machine translation
Neural network
Morphology
Vocabulary
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Machine translating
Machine translation
Neural network
Morphology
Vocabulary
Traducció automàtica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description This article has been published in a revised form in Natural Language Engineering https://doi.org/10.1017/S1351324920000364. This version is free to view and download for private research and study only. Not for re-distribution, re-sale or use in derivative works. © Cambridge University Press
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-01-01
2020
2020-10-26
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/330835
https://dx.doi.org/10.1017/S1351324920000364
url https://hdl.handle.net/2117/330835
https://dx.doi.org/10.1017/S1351324920000364
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad http://doi.org/10.13039/501100003329 TEC2015-69266-P TECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ Y AUDIO
Agencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación (PEICTI) 2013-2016 PCIN-2017-079 AUTONOMOUS LIFELONG LEARNING INTELLIGENT SYSTEMS
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
application/pdf
dc.publisher.none.fl_str_mv Cambridge University Press
publisher.none.fl_str_mv Cambridge University Press
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_ 1869405415607894016
score 15,300724

Similares en LA Referencia