[Solved] Given the following code snippet using Gensim's Word2Vec with CBOW, what... Given the following code snippet using Gensim's Word2Vec with CBOW, what will be the shape of the learned word vectors? | NLP

NLP - Word Embeddings

Given the following code snippet using Gensim's Word2Vec with CBOW, what will be the shape of the learned word vectors? from gensim.models import Word2Vec sentences = [['cat', 'sat', 'on', 'mat'], ['dog', 'barked', 'loudly']] model = Word2Vec(sentences, vector_size=50, window=2, sg=0, min_count=1) print(model.wv['cat'].shape)

A(4, 50)

B(50,)

C(2, 50)

D(1, 50)

Step-by-Step Solution

Solution:

Step 1: Understand vector_size parameter
The vector_size=50 means each word is represented by a 50-dimensional vector.
Step 2: Check output of model.wv[word]
model.wv[word] returns a 1D numpy array of length 50, so shape is (50,).
Final Answer:
(50,) -> Option B
Quick Check:
Word vector shape = vector_size [OK]

Quick Trick: Word vectors have shape equal to vector_size [OK]

Common Mistakes:

MISTAKES

Confusing window size with vector size
Expecting 2D shape for single word vector
Assuming shape depends on sentence length

Master "Word Embeddings" in NLP

9 interactive learning modes - each teaches the same concept differently

Learn Why Deep Model Try Challenge Experiment Recall Metrics

More NLP Quizzes

Given the following code snippet using Gensim's Word2Vec with CBOW, what will be the shape of the learned word vectors?

Step 1: Understand vector_size parameter

Step 2: Check output of model.wv[word]

Final Answer:

Quick Check:

Want More Practice?