Neural machine translation

Neural machine translation (also known as NMT) is a method of machine translation performed with recurrent neural networks (RNN).
An encoder encrypts sequences of words in the source text in vectors.
A decoder then decrypts these vectors and decodes the target text word by word.
By taking greater account of the overall context of the words, well-formed translations are generated, both grammatically and stylistically, which are not always correct in terms of content.