Training Word2Vec with Gensim in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this Word2Vec training snippet?

Consider the following code that trains a Word2Vec model on a small corpus. What will be the shape of the vector for the word 'king' after training?

NLP

from gensim.models import Word2Vec
sentences = [['king', 'queen', 'man', 'woman'], ['apple', 'orange', 'fruit'], ['king', 'man', 'apple']]
model = Word2Vec(sentences, vector_size=50, window=2, min_count=1, epochs=10)
vector = model.wv['king']
print(vector.shape)

A (100,)

B (10,)

C (50,)

D (1, 50)

💡 Hint

Check the vector_size parameter in the Word2Vec constructor.

The vector_size parameter sets the dimensionality of the word vectors. Here it is 50, so the vector for any word will have shape (50,).

❓ Model Choice

intermediate

Which Word2Vec parameter controls the size of the context window?

You want to train a Word2Vec model and control how many words before and after the target word are considered as context. Which parameter do you set?

A vector_size

B epochs

C min_count

D window

💡 Hint

Think about the number of words around the target word.

The 'window' parameter defines the maximum distance between the current and predicted word within a sentence, i.e., the context window size.

❓ Hyperparameter

advanced

Which parameter affects ignoring infrequent words during Word2Vec training?

You want to exclude words that appear less than a certain number of times in your corpus to speed up training and reduce noise. Which Word2Vec parameter do you adjust?

A window

B min_count

C vector_size

D sg

💡 Hint

This parameter filters out rare words.

The 'min_count' parameter sets the minimum frequency threshold for words to be included in the vocabulary.

❓ Metrics

advanced

Which metric can you use to evaluate the quality of Word2Vec embeddings?

After training a Word2Vec model, you want to check if the embeddings capture semantic similarity well. Which metric or method is commonly used?

A Cosine similarity between word vectors

B Mean squared error on training loss

C Accuracy on classification labels

D Confusion matrix of predicted words

💡 Hint

Think about measuring similarity between vectors.

Cosine similarity measures how close two word vectors are in direction, which reflects semantic similarity.

🔧 Debug

expert

Why does this Word2Vec training code raise a KeyError?

You run this code and get a KeyError when accessing the vector for 'banana'. What is the cause?

NLP

from gensim.models import Word2Vec
sentences = [['apple', 'orange', 'fruit'], ['king', 'queen', 'man', 'woman']]
model = Word2Vec(sentences, vector_size=20, window=2, min_count=2, epochs=5)
vector = model.wv['banana']

A 'banana' is not in the vocabulary because it does not appear at least twice (min_count=2)

B The vector_size is too small to store 'banana' vector

C The window size is too small to include 'banana'

D The epochs parameter is too low to train 'banana' vector

💡 Hint

Check the min_count parameter and the words in the sentences.

Since 'banana' never appears in the sentences, and min_count=2 filters out words appearing less than twice, 'banana' is not in the vocabulary, causing KeyError.