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

By Martin Popel, Markéta Tomková, Jakub Tomek, Łukasz Kaiser, Jakob Uszkoreit, Ondrej Bojar, Zdenek Zabokrtský. Nature Communications, 2020

331 citations recorded by the source corpus.

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. 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2bb861fc09912a56aed0c652e9b764edba56bb0c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

A comprehensive review on ensemble deep learning: Opportunities and challenges (2023, unknown): “Machine translation (Popel et al., 2020; Popel et al., 2020).”
Findings of the 2020 Conference on Machine Translation (WMT20) (2020, methodology): “It is the Transformer model trained according to Popel and Bojar (2018) plus a novel concat-regime backtranslation with checkpoint averaging (Popel et al., 2020), tuned separately for CZ-domain and non CZ-domain articles, possibly handling also translation-direction (“translationese”) issues.”
A Cookbook of Self-Supervised Learning (2023, background): “Self-supervised learning (SSL) underpins deep learning’s success in natural language processing leading to advances from automated machine translation to large language models trained on web-scale corpora of unlabeled text [Brown et al., 2020, Popel et al., 2020].”
Multi-scale modeling in thermal conductivity of Polyurethane incorporated with Phase Change Materials using Physics-Informed Neural Networks (2023, background): “It has proven its effectiveness in computer vision [22], speech recognition [23], natural language processing [24], and strategic games [25, 26], as well as in drug development [27].”
Findings of the 2021 Conference on Machine Translation (WMT21) (2021, methodology): “A similar setup has been used by Popel et al. (2020) even for more than two systems compared at once.”