Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals

The quality of human language translation has been thought to be unattainable by computer translation systems. Here the authors present CUBBITT, a deep learning system that outperforms professional human translators in retaining text meaning in English-to-Czech news translation, and validate the sys...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Martin Popel, Marketa Tomkova, Jakub Tomek, Łukasz Kaiser, Jakob Uszkoreit, Ondřej Bojar, Zdeněk Žabokrtský
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/a659b74d79c2411697adc8096cdc92e3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a659b74d79c2411697adc8096cdc92e3
record_format	dspace
spelling	oai:doaj.org-article:a659b74d79c2411697adc8096cdc92e32021-12-02T19:09:31ZTransforming machine translation: a deep learning system reaches news translation quality comparable to human professionals10.1038/s41467-020-18073-92041-1723https://doaj.org/article/a659b74d79c2411697adc8096cdc92e32020-09-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-18073-9https://doaj.org/toc/2041-1723The quality of human language translation has been thought to be unattainable by computer translation systems. Here the authors present CUBBITT, a deep learning system that outperforms professional human translators in retaining text meaning in English-to-Czech news translation, and validate the system on English-French and English-Polish language pairs.Martin PopelMarketa TomkovaJakub TomekŁukasz KaiserJakob UszkoreitOndřej BojarZdeněk ŽabokrtskýNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-15 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Martin Popel Marketa Tomkova Jakub Tomek Łukasz Kaiser Jakob Uszkoreit Ondřej Bojar Zdeněk Žabokrtský Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
description	The quality of human language translation has been thought to be unattainable by computer translation systems. Here the authors present CUBBITT, a deep learning system that outperforms professional human translators in retaining text meaning in English-to-Czech news translation, and validate the system on English-French and English-Polish language pairs.
format	article
author	Martin Popel Marketa Tomkova Jakub Tomek Łukasz Kaiser Jakob Uszkoreit Ondřej Bojar Zdeněk Žabokrtský
author_facet	Martin Popel Marketa Tomkova Jakub Tomek Łukasz Kaiser Jakob Uszkoreit Ondřej Bojar Zdeněk Žabokrtský
author_sort	Martin Popel
title	Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
title_short	Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
title_full	Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
title_fullStr	Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
title_full_unstemmed	Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
title_sort	transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/a659b74d79c2411697adc8096cdc92e3
work_keys_str_mv	AT martinpopel transformingmachinetranslationadeeplearningsystemreachesnewstranslationqualitycomparabletohumanprofessionals AT marketatomkova transformingmachinetranslationadeeplearningsystemreachesnewstranslationqualitycomparabletohumanprofessionals AT jakubtomek transformingmachinetranslationadeeplearningsystemreachesnewstranslationqualitycomparabletohumanprofessionals AT łukaszkaiser transformingmachinetranslationadeeplearningsystemreachesnewstranslationqualitycomparabletohumanprofessionals AT jakobuszkoreit transformingmachinetranslationadeeplearningsystemreachesnewstranslationqualitycomparabletohumanprofessionals AT ondrejbojar transformingmachinetranslationadeeplearningsystemreachesnewstranslationqualitycomparabletohumanprofessionals AT zdenekzabokrtsky transformingmachinetranslationadeeplearningsystemreachesnewstranslationqualitycomparabletohumanprofessionals
_version_	1718377107842662400

Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals

Ejemplares similares