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 and Zdeněk Žabokrtský
Additional contact information
Martin Popel: Charles University
Marketa Tomkova: University of Oxford
Jakub Tomek: University of Oxford
Łukasz Kaiser: Google Brain, Mountain View
Jakob Uszkoreit: Google Brain, Mountain View
Ondřej Bojar: Charles University
Zdeněk Žabokrtský: Charles University

Nature Communications, 2020, vol. 11, issue 1, 1-15

Abstract: Abstract The quality of human translation was long thought to be unattainable for computer translation systems. In this study, we present a deep-learning system, CUBBITT, which challenges this view. In a context-aware blind evaluation by human judges, CUBBITT significantly outperformed professional-agency English-to-Czech news translation in preserving text meaning (translation adequacy). While human translation is still rated as more fluent, CUBBITT is shown to be substantially more fluent than previous state-of-the-art systems. Moreover, most participants of a Translation Turing test struggle to distinguish CUBBITT translations from human translations. This work approaches the quality of human translation and even surpasses it in adequacy in certain circumstances.This suggests that deep learning may have the potential to replace humans in applications where conservation of meaning is the primary aim.

Date: 2020
References: Add references at CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
https://www.nature.com/articles/s41467-020-18073-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-18073-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-020-18073-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().