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

Martin Popel; Marketa Tomkova; Jakub Tomek; Łukasz Kaiser; Jakob Uszkoreit; Ondřej Bojar; Zdeněk Žabokrtský

doi:10.1038/s41467-020-18073-9

Nature Communications (Sep 2020)

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

Martin Popel,
Marketa Tomkova,
Jakub Tomek,
Łukasz Kaiser,
Jakob Uszkoreit,
Ondřej Bojar,
Zdeněk Žabokrtský

Affiliations

Martin Popel: Faculty of Mathematics and Physics, Charles University
Marketa Tomkova: Ludwig Cancer Research Oxford, University of Oxford
Jakub Tomek: Department of Computer Science, University of Oxford
Łukasz Kaiser: Google Brain, Mountain View
Jakob Uszkoreit: Google Brain, Mountain View
Ondřej Bojar: Faculty of Mathematics and Physics, Charles University
Zdeněk Žabokrtský: Faculty of Mathematics and Physics, Charles University

DOI: https://doi.org/10.1038/s41467-020-18073-9
Journal volume & issue: Vol. 11, no. 1
pp. 1 – 15

Abstract

Read online

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.

Published in Nature Communications

ISSN: 2041-1723 (Online)
Publisher: Nature Portfolio
Country of publisher: United Kingdom
LCC subjects: Science
Website: https://www.nature.com/ncomms/

About the journal