THE DEEP-LEARNING UPGRADE OF GOOGLE TRANSLATION METHODS

About the authors:

Minyaylo M.I., Bachelor student, University of Tyumen, manyakos2@yandex.ru
Skorokhodova L. , Tyumen State University, Department of Foreign Languages and Professional Cross-cultural Communication IMSIT senior lecturer

Abstract:

It seems to be a generally accepted belief that NMT systems are computationally expensive both in training and in translation inference. They also lack of robustness, particularly when input sentences contain rare words, very large data sets and large models.
Google Neural Machine Translation (NMT) has great potential to overcome many of the weaknesses of conventional phrase-based translation systems. Google began experimenting with a deep-learning technique, called neural machine translation that can translate entire sentences without breaking them down into smaller components. That approach eventually reduced the number of Google Translate errors by at least 60 percent on many language pairs in comparison with the older, phrase-based approach.

References: