Machine translation

So far, we have seen a scenario where the input and output are mapped one-to-one. In this section, we will look into ways in which we can construct architectures that result in mapping all input data into a vector, and then decoding it into the output vector.

We will be translating an input text in English into text in French in this case study.

Getting ready

The architecture that we will be defining to perform machine translation is as follows:

• Take a labeled dataset where the input sentence and the corresponding translation in French is available
• Tokenize and extract words that are frequent in each of the English and French texts:
  • To identify the frequent words, we will count the frequency of each word...