Part 2: Text reversing model - Encoder

You will now implement the rest of the encoder of the text reversing model. The encoder feeds on the one-hot vectors produced by the words2onehot() function you implemented previously.

Here you will be implementing the encoder() function. The encoder() function takes in a set of one-hot vectors and converts them to a list of word ids.

For this exercise, the words2onehot() function and the word2index dictionary (having the words We, like and dogs) have been provided.

Deze oefening maakt deel uit van de cursus

Machine Translation with Keras

Cursus bekijken

Oefeninstructies

Convert onehot to an array of word IDs using np.argmax() function and return the word IDs.
Define a list of words with words We, like, dogs.
Convert the list of words to onehot vectors using the words2onehot() function. Remember that words2onehot() takes a list of words and a Python dictionary as its arguments.
Get the context vector of the onehot vectors using the encoder() function.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

def encoder(onehot):
  # Get word IDs from onehot vectors and return the IDs
  word_ids = np.____(____, axis=____)
  return ____

# Define "We like dogs" as words
words = ____
# Convert words to onehot vectors using words2onehot
onehot = ____(____, ____)
# Get the context vector by using the encoder function
context = encoder(____)
print(context)

Code bewerken en uitvoeren