Translating sentences

Another of deep learning in text has got its boost in performance and popularity thanks to a couple of large search engines. Translating sentences is a hard task because each language has its own rules, exceptions, and expressions. What we tend to forget is that the translation of words often largely depends on the context around it. Some believe that solving a language thoroughly can be a huge milestone for achieving general AI, because intelligence and language are well connected and small nuances in language can be crucial to understanding.

In our next recipe, we will demonstrate how to use a sequence-to-sequence model to translate sentences from English to French. We will be using the CNTK framework. 

How to do it...

1. Let's start with loading the libraries:

import numpy as np
import os

from cntk import Trainer, Axis
from cntk.io import MinibatchSource, CTFDeserializer, StreamDef, StreamDefs, INFINITELY_REPEAT
from cntk.learners import momentum_sgd, fsadagrad, momentum_as_time_constant_schedule...