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

Popel M., Tomkova M., Tomek J., Kaiser Ł., Uszkoreit J., Bojar O., Žabokrtský Z.

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.

DOI

10.1038/s41467-020-18073-9

Type

Journal article

Journal

Nature communications

Publication Date

09/2020

Volume

11

Addresses

Faculty of Mathematics and Physics, Charles University, Prague, 121 16, Czech Republic. popel@ufal.mff.cuni.cz.

Permalink Original publication