[1][2][3][4] The neural network consisted of two main blocks, an encoder and a decoder, both of LSTM architecture with 8 1024-wide layers each and a simple 1-layer 1024-wide feedforward attention mechanism connecting them.
[2] GNMT's proposed architecture of system learning was first tested on over a hundred languages supported by Google Translate.
Google Translate's NMT system uses a large artificial neural network capable of deep learning.
[1] GNMT's proposed architecture of system learning was first tested on over a hundred languages supported by Google Translate.
[23] The new translation engine was first enabled for eight languages: to and from English and French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish in November 2016.
[27] In mid April 2017 Google Netherlands announced support for Dutch and other European languages related to English.
[28] Further support was added for nine Indian languages: Hindi, Bengali, Marathi, Gujarati, Punjabi, Tamil, Telugu, Malayalam and Kannada at the end of April 2017.