Translations:Attention Is All You Need/21/en

On the WMT 2014 English-to-German translation task, the big transformer model achieved a bleu score of 28.4, surpassing the previous best results including ensembles by over 2 bleu points. On the WMT 2014 English-to-French task, it achieved 41.0 bleu, establishing a new single-model state-of-the-art at a fraction of the training cost of prior models.