Generating word vectors
In this exercise, we will generate the pairwise similarity scores of all the words in a sentence. The sentence is available as sent and has been printed to the console for your convenience.
Deze oefening maakt deel uit van de cursus
Feature Engineering for NLP in Python
Oefeninstructies
- Create a
Docobjectdocforsent. - In the nested loop, compute the similarity between
token1andtoken2.
Praktische interactieve oefening
Probeer deze oefening eens door deze voorbeeldcode in te vullen.
# Create the doc object
doc = nlp(___)
# Compute pairwise similarity scores
for token1 in doc:
for token2 in doc:
print(token1.text, token2.text, token1.similarity(token2))