Exercise

Bag-of-words picker

It's time for a quick check on your understanding of bag-of-words. Which of the below options, with basic nltk tokenization, map the bag-of-words for the following text?

"The cat is in the box. The cat box."

Instructions

50 XP

Possible answers

('the', 3), ('box.', 2), ('cat', 2), ('is', 1)

('The', 3), ('box', 2), ('cat', 2), ('is', 1), ('in', 1), ('.', 1)

('the', 3), ('cat box', 1), ('cat', 1), ('box', 1), ('is', 1), ('in', 1)

('The', 2), ('box', 2), ('.', 2), ('cat', 2), ('is', 1), ('in', 1), ('the', 1)