Practice More Questions From: Week 4 Quiz
Q:
When predicting words to generate poetry, the more words predicted the more likely it will end up gibberish. Why?
Q:
What is a major drawback of word-based training for text generation instead of character-based generation?
Q:
What are the critical steps in preparing the input sequences for the prediction model?
Q:
In natural language processing, predicting the next item in a sequence is a classification problem.Therefore, after creating inputs and labels from the subphrases, we one-hot encode the labels. What function do we use to create one-hot encoded arrays of the labels?
Q:
True or False: When building the model, we use a sigmoid activated Dense output layer with one neuron per word that lights up when we predict a given word.
Subscribe
0 Comments