Exploring word relationships with embeddings
Word embeddings capture the meanings of words based on their usage in large text datasets. By placing similar words closer together in a continuous vector space, they allow models to recognize context and semantic relationships that more basic methods can't capture. Now You'll work with embeddings to explore these kinds of word relationships firsthand.
The glove-wiki-gigaword-50 word embedding model has been successfully loaded and is ready for use through the variable model_glove_wiki.
This exercise is part of the course
Natural Language Processing (NLP) in Python
Exercise instructions
- Compute the similarity score between
"king"and"queen". - Get the top 10 most similar words to
"computer".
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Compute similarity between "king" and "queen"
similarity_score = model_glove_wiki.____
print(similarity_score)
# Get top 10 most similar words to "computer"
similar_words = model_glove_wiki.____
print(similar_words)