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.

Practice

1. What is the main purpose of training a Word2Vec model using Gensim?

easy

A. To count the frequency of words in a text

B. To translate text from one language to another

C. To convert words into meaningful number vectors

D. To remove stop words from a text

Solution

1. Step 1: Understand Word2Vec's goal

   Word2Vec creates number vectors that capture word meanings and relationships.

2. Step 2: Identify Gensim's role

   Gensim provides tools to train Word2Vec models easily on text data.

3. Final Answer:

   To convert words into meaningful number vectors -> Option C

4. Quick Check:

   Word2Vec = word vectors [OK]

Hint: Word2Vec = words to numbers with meaning [OK]

Common Mistakes:

• Confusing Word2Vec with word counting
• Thinking Word2Vec translates languages
• Assuming Word2Vec removes stop words

2. Which of the following is the correct way to import the Word2Vec class from Gensim?

easy

A. from gensim.models import Word2Vec

B. import Word2Vec from gensim.models

C. from gensim import Word2Vec

D. import gensim.Word2Vec

Solution

1. Step 1: Recall Python import syntax

   Correct import uses 'from module import class' format.

2. Step 2: Match Gensim's Word2Vec import

   Gensim's Word2Vec is in gensim.models, so 'from gensim.models import Word2Vec' is correct.

3. Final Answer:

   from gensim.models import Word2Vec -> Option A

4. Quick Check:

   Correct import syntax = from gensim.models import Word2Vec [OK]

Hint: Use 'from module import class' for classes [OK]

Common Mistakes:

• Using wrong import order
• Trying to import directly from gensim
• Using invalid import syntax

3. Given the code below, what will be the output of print(model.wv['king'])?

from gensim.models import Word2Vec
sentences = [['king', 'queen', 'man', 'woman'], ['apple', 'banana', 'fruit']]
model = Word2Vec(sentences, vector_size=10, window=2, min_count=1, epochs=5)
print(model.wv['king'])

medium

A. A 10-dimensional numpy array representing 'king'

B. The string 'king'

C. A list of words similar to 'king'

D. An error because 'king' is not in vocabulary

Solution

1. Step 1: Understand model.wv['word'] output

   Accessing model.wv['king'] returns the vector (array) for 'king'.

2. Step 2: Check training and vocabulary

   'king' is in sentences and min_count=1, so it's in vocabulary and has a vector of size 10.

3. Final Answer:

   A 10-dimensional numpy array representing 'king' -> Option A

4. Quick Check:

   model.wv['word'] = vector array [OK]

Hint: model.wv[word] returns vector array [OK]

Common Mistakes:

• Expecting a string instead of vector
• Confusing with similar words list
• Assuming 'king' is missing from vocabulary

4. What is wrong with this code snippet for training Word2Vec?

from gensim.models import Word2Vec
sentences = [['cat', 'dog'], ['mouse', 'rat']]
model = Word2Vec(sentences, size=50, window=3, min_count=1)
model.train(sentences, total_examples=2, epochs=10)

medium

A. min_count must be greater than 1

B. 'train' method is missing required arguments

C. Sentences should be a flat list, not list of lists

D. The parameter 'size' is deprecated; use 'vector_size' instead

Solution

1. Step 1: Check Word2Vec parameters

   Recent Gensim versions use 'vector_size' instead of 'size' for vector dimension.

2. Step 2: Verify other code parts

   'train' method usage and sentences format are correct; min_count=1 is valid.

3. Final Answer:

   The parameter 'size' is deprecated; use 'vector_size' instead -> Option D

4. Quick Check:

   Use 'vector_size' not 'size' [OK]

Hint: Use 'vector_size' for dimensions in Gensim 4+ [OK]

Common Mistakes:

• Using old 'size' parameter causes warnings or errors
• Thinking sentences must be flat list
• Believing min_count must be >1

5. You want to train a Word2Vec model on a large text corpus but notice the training is very slow. Which combination of changes can speed up training without losing much quality?

1. Reduce vector_size from 300 to 100
2. Increase window size from 5 to 10
3. Set min_count to 5 instead of 1
4. Decrease epochs from 10 to 3

hard

A. Apply changes 2 and 4 only

B. Apply changes 1, 3, and 4

C. Apply changes 1 and 3 only

D. Apply all changes 1, 2, 3, and 4

Solution

1. Step 1: Analyze each change's effect on speed and quality

   Reducing vector_size (1) speeds training with slight quality loss. Increasing window (2) slows training and may reduce quality. Increasing min_count (3) removes rare words, speeding training. Decreasing epochs (4) reduces training time but may reduce quality.

2. Step 2: Choose changes that speed up without much quality loss

   Changes 1, 3, and 4 speed training; 2 increases window and slows it, so exclude 2.

3. Final Answer:

   Apply changes 1, 3, and 4 -> Option B

4. Quick Check:

   Reduce size, min_count, epochs = faster training [OK]

Hint: Lower vector_size, min_count, epochs to speed up [OK]

Common Mistakes:

• Increasing window size slows training
• Ignoring min_count effect on vocabulary size
• Reducing epochs too much hurts quality