Deep Neural Transformer Model for Mono and Multi Lingual Machine Translation
No Thumbnail Available
Date
2021-05-25
Journal Title
Journal ISSN
Volume Title
Publisher
University of Oum El Bouaghi
Abstract
In recent years, the Transformers have emerged as the most relevant deep architecture, especially machine translation. These models, which are based on attention mechanisms, outperformed previous neural machine translation architectures in several tasks.
This paper proposes a new architecture based on the transformer model for the monolingual and multilingual translation system. The tests were carried out on the IWSLT 2015 and 2016 dataset.
The Transformers attention mechanism increases the accuracy to more than 92% that we can quantify by more than 4 BLEU points (a performance metric used in machine translation
systems).