Vocabulary size control in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why limit vocabulary size in NLP models?

In natural language processing, why do we often limit the vocabulary size when building models?

A To reduce model complexity and memory usage while focusing on the most frequent words

B To make the model ignore common words like 'the' and 'and'

C To increase the number of rare words the model can learn

D To ensure the model only learns from stop words

💡 Hint

Think about how large vocabularies affect model size and training speed.

Limiting vocabulary size helps keep the model smaller and faster by focusing on frequent words, which carry most meaning. Rare words are often replaced with a special token.

❓ Predict Output

intermediate

Output of vocabulary size after filtering

Given the code below that filters tokens by frequency, what is the length of the resulting vocabulary?

NLP

from collections import Counter

texts = ['apple banana apple', 'banana orange apple', 'orange banana banana']
tokens = ' '.join(texts).split()
counter = Counter(tokens)
vocab = {word for word, freq in counter.items() if freq >= 3}
print(len(vocab))

A 2

B 3

C 1

D 0

💡 Hint

Count how many words appear at least 3 times.

'apple' appears 3 times, 'banana' 4 times, 'orange' 2 times. Only 'apple' and 'banana' meet the frequency threshold.

❓ Model Choice

advanced

Choosing a tokenization method to control vocabulary size

You want to control vocabulary size in a text classification task. Which tokenization method helps best to keep vocabulary size manageable while capturing meaningful subword units?

A Character-level tokenization

B Word-level tokenization without filtering

C Sentence-level tokenization

D Byte Pair Encoding (BPE) subword tokenization

💡 Hint

Think about methods that break words into smaller parts to reduce vocabulary size.

BPE breaks words into subword units, reducing vocabulary size while preserving meaning better than character-level tokenization.

❓ Metrics

advanced

Effect of vocabulary size on model perplexity

When training a language model, how does increasing vocabulary size generally affect the model's perplexity on test data?

A Perplexity always decreases as vocabulary size increases

B Perplexity may increase due to data sparsity with very large vocabularies

C Perplexity always increases as vocabulary size decreases

D Perplexity remains unchanged regardless of vocabulary size

💡 Hint

Consider the trade-off between vocabulary coverage and data sparsity.

Very large vocabularies cause many rare words, leading to sparse data and higher perplexity. Moderate vocabularies balance coverage and data density.

🔧 Debug

expert

Identifying the bug in vocabulary size control code

What error does the following code raise when trying to limit vocabulary size by frequency?

from collections import Counter
texts = ['cat dog cat', 'dog mouse cat', 'mouse dog dog']
tokens = ' '.join(texts).split()
counter = Counter(tokens)
vocab = {word for word in counter if counter[word] > 2}
print(vocab[0])

A SyntaxError: invalid syntax

B KeyError: 0

C TypeError: 'set' object is not subscriptable

D No error, prints 'cat'

💡 Hint

Look at how vocab is accessed after creation.

vocab is a set, which cannot be accessed by index like a list. Trying vocab[0] causes a TypeError.

Practice

1. What is the main purpose of controlling vocabulary size in NLP models?

easy

A. To add more rare words to the dataset

B. To increase the number of training epochs

C. To limit the number of words the model uses

D. To make the model ignore stop words

Solution

1. Step 1: Understand vocabulary size control

   Vocabulary size control means setting a limit on how many unique words the model can use.

2. Step 2: Identify the main goal

   The goal is to reduce complexity and noise by ignoring very rare words, so the model focuses on common words.

3. Final Answer:

   To limit the number of words the model uses -> Option C

4. Quick Check:

   Vocabulary size control = limit words [OK]

Hint: Vocabulary size control means limiting words used [OK]

Common Mistakes:

• Thinking it increases training epochs
• Believing it adds rare words
• Confusing it with stop word removal

2. Which parameter in scikit-learn's CountVectorizer controls the vocabulary size?

easy

A. max_features

B. min_df

C. stop_words

D. ngram_range

Solution

1. Step 1: Recall CountVectorizer parameters

   CountVectorizer has parameters like max_features, min_df, stop_words, and ngram_range.

2. Step 2: Identify parameter for vocabulary size

   max_features sets the maximum number of words (features) to keep, controlling vocabulary size.

3. Final Answer:

   max_features -> Option A

4. Quick Check:

   max_features controls vocabulary size [OK]

Hint: max_features sets max vocabulary size in vectorizers [OK]

Common Mistakes:

• Choosing min_df which filters by document frequency
• Confusing stop_words with vocabulary size
• Thinking ngram_range controls vocabulary size

3. What will be the output vocabulary size after running this code?

from sklearn.feature_extraction.text import CountVectorizer
texts = ['apple banana apple', 'banana orange', 'apple orange orange']
vectorizer = CountVectorizer(max_features=2)
vectorizer.fit(texts)
vocab = vectorizer.get_feature_names_out()
print(len(vocab))

medium

A. 3

B. 2

C. 4

D. 1

Solution

1. Step 1: Understand max_features effect

   max_features=2 means the vectorizer keeps only the top 2 most frequent words.

2. Step 2: Count unique words and frequencies

   Words: apple(3), banana(2), orange(3). Top 2 are apple and orange.

3. Final Answer:

   2 -> Option B

4. Quick Check:

   max_features=2 means vocabulary size = 2 [OK]

Hint: max_features limits vocabulary count to given number [OK]

Common Mistakes:

• Counting all unique words ignoring max_features
• Assuming max_features is minimum count
• Confusing frequency with vocabulary size

4. Identify the error in this code snippet that tries to limit vocabulary size:

from sklearn.feature_extraction.text import CountVectorizer
texts = ['cat dog', 'dog mouse', 'cat mouse']
vectorizer = CountVectorizer(max_features='3')
vectorizer.fit(texts)
vocab = vectorizer.get_feature_names_out()
print(vocab)

medium

A. max_features should be an integer, not a string

B. fit() should be replaced with fit_transform()

C. get_feature_names_out() is deprecated

D. texts should be a numpy array

Solution

1. Step 1: Check max_features type

   max_features expects an integer, but '3' is a string, causing a type error.

2. Step 2: Confirm other parts are correct

   fit() works fine, get_feature_names_out() is current method, texts can be list.

3. Final Answer:

   max_features should be an integer, not a string -> Option A

4. Quick Check:

   max_features type must be int [OK]

Hint: max_features must be int, not string [OK]

Common Mistakes:

• Using string instead of integer for max_features
• Thinking fit_transform is required here
• Believing get_feature_names_out is deprecated

5. You want to build a text classifier but your dataset has 100,000 unique words. To speed up training and reduce noise, which approach best controls vocabulary size?

hard

A. Increase max_features to 200,000 to include more words

B. Use all 100,000 words to keep maximum information

C. Remove stop words only without limiting vocabulary size

D. Set max_features to a smaller number like 5000 in your vectorizer

Solution

1. Step 1: Understand problem with large vocabulary

   100,000 words is large and slows training; many words may be rare and noisy.

2. Step 2: Choose best vocabulary control method

   Setting max_features to a smaller number like 5000 keeps common words and speeds training.

3. Final Answer:

   Set max_features to a smaller number like 5000 in your vectorizer -> Option D

4. Quick Check:

   Limit vocabulary size to speed training [OK]

Hint: Limit vocabulary size to speed training and reduce noise [OK]

Common Mistakes:

• Using all words causing slow training
• Only removing stop words without size control
• Increasing max_features unnecessarily