Word vectors in spaCy vocabulary
The purpose of word vectors is to allow a computer to understand words. In this exercise, you will practice extracting word vectors for a given list of words.
A list of words is compiled as words
. The en_core_web_md
model is already imported and available as nlp
.
The vocabulary of en_core_web_md
model contains 20,000 words. If a word does not exist in the vocabulary, you will not be able to extract its corresponding word vector. In this exercise, for simplicity, it is ensured that all the given words exist in this model's vocabulary.
This exercise is part of the course
Natural Language Processing with spaCy
Exercise instructions
- Extract the IDs of all the given
words
and store them in anids
list. - For each ID from
ids
, store the first ten elements of the word vector in theword_vectors
list. - Print the first ten elements of the first word vector from
word_vectors
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
words = ["like", "love"]
# IDs of all the given words
ids = [nlp.____.____[w] for w in words]
# Store the first ten elements of the word vectors for each word
word_vectors = [nlp.____.____[i][:10] for i in ids]
# Print the first ten elements of the first word vector
print(____[0])