Defining a model for neural machine translation

As stated earlier, the encoder will process the source input sequence through an LSTM and encode the source text into a meaningful summary. The meaningful summary would be stored in the final sequence step hidden and cell states hf and cf. These vectors together (that is, [hf; cf]) provide a meaningful context about the source text, and the decoder is trained to produce its own target sequence conditioned on the hidden and cell state vectors [hf; cf].

Illustrated in the following diagram, Figure 3.5, is a detailed diagram of the training process of an English-to-French translation. The English sentence It's a beautiful day is converted to a meaning summary through an LSTM, which is then stored ...

Get Intelligent Projects Using Python now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.