For this activity follow Neural machine translation with a Transformer and Keras.
Submit completed Colab notebook showing generated output.
Dataset - The tutorial uses a English/Portuguese dataset, which consists of million s of sentence pairs, with English sentences on one side and their Portuguese translations on the other side. The dataset is preprocessed/tokenized, in order to easily be used in the training model.
Transformer Components - The transformer model is composed of two components, the encoder and the decoder. The encoder takes in the input sequence and produces a set of encoded representations. The decoder takes in the encoded representations and produces the output sequence. Both the encoder and decoder seem to be composed of multiple layers of feedforward neural networks.