Journal article icon

Journal article

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

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.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1038/s41467-020-18073-9

Authors

More by this author
Role:
Author
ORCID:
0000-0002-3628-8419
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
NDM
Role:
Author
ORCID:
0000-0001-9094-2365
More by this author
Institution:
University of Oxford
Division:
MSD
Sub department:
AV PHYSIOLOGY ANATOMY AND GENETICS; BL COMPUTER SCIENCE; DD DOCTORAL TRAINING CENTRE - MPLS
Role:
Author
ORCID:
0000-0002-0157-4386
More by this author
Role:
Author
ORCID:
0000-0003-1092-6010
More by this author
Role:
Author
ORCID:
0000-0001-5066-7530


Publisher:
Springer Nature
Journal:
Nature Communications More from this journal
Volume:
11
Issue:
1
Article number:
4381
Publication date:
2020-09-01
Acceptance date:
2020-07-24
DOI:
EISSN:
2041-1723
Pmid:
32873773


Language:
English
Keywords:
Pubs id:
1130814
Local pid:
pubs:1130814
Deposit date:
2020-12-17
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP