N-gram language models in NLP

Introduction

N-gram language models help computers guess the next word in a sentence by looking at the last few words. This makes talking to machines feel more natural.

When building a simple text predictor like a phone keyboard suggestion.

When checking if a sentence sounds natural or not.

When creating a basic chatbot that replies with common phrases.

When analyzing how often word groups appear in a book or article.

Syntax

NLP

def n_gram_model(text, n):
    tokens = text.split()
    n_grams = [tuple(tokens[i:i+n]) for i in range(len(tokens)-n+1)]
    return n_grams

The function splits text into words and groups them into sequences of length n.

Each group is called an n-gram, like pairs (bigrams) or triples (trigrams).

Examples

Returns bigrams: [('I', 'love'), ('love', 'machine'), ('machine', 'learning')]

NLP

n_gram_model('I love machine learning', 2)

Returns unigrams (single words): [('Hello',), ('world',)]

NLP

n_gram_model('Hello world', 1)

Returns trigrams: [('Data', 'science', 'is'), ('science', 'is', 'fun')]

NLP

n_gram_model('Data science is fun', 3)

Sample Model

This program splits a sentence into bigrams (pairs of words), counts how often each pair appears, and prints the counts.

NLP

from collections import Counter

def n_gram_model(text, n):
    tokens = text.lower().split()
    n_grams = [tuple(tokens[i:i+n]) for i in range(len(tokens)-n+1)]
    return n_grams

# Sample text
text = 'I love machine learning and I love coding'

# Create bigrams
bigrams = n_gram_model(text, 2)

# Count frequency of each bigram
bigram_counts = Counter(bigrams)

print('Bigrams and their counts:')
for bigram, count in bigram_counts.items():
    print(f'{bigram}: {count}')

Important Notes

N-gram models are simple but can miss meaning because they only look at a few words at a time.

They work best with lots of text to learn common word patterns.

Higher n (like 3 or 4) means more context but needs more data and computing power.

Summary

N-gram models group words into sequences to predict or analyze text.

They are easy to build and useful for simple language tasks.

Counting n-grams helps understand common word patterns in text.

Practice

1. What does an n-gram language model primarily do?

easy

A. Predict the next word based on previous words

B. Translate text from one language to another

C. Generate images from text descriptions

D. Detect the sentiment of a sentence

Solution

1. Step 1: Understand the purpose of n-gram models

   N-gram models look at sequences of words to predict what comes next.

2. Step 2: Identify the main function

   They use previous words to guess the next word in a sentence.

3. Final Answer:

   Predict the next word based on previous words -> Option A

4. Quick Check:

   N-gram models predict next word = A [OK]

Hint: N-grams predict next word from previous words [OK]

Common Mistakes:

• Confusing n-gram with translation models
• Thinking n-grams generate images
• Mixing up sentiment analysis with n-grams

2. Which of the following is the correct way to represent a bigram from the sentence 'I love AI'?

easy

A. ('AI', 'love')

B. ('I', 'love')

C. ('love', 'AI', 'I')

D. ('I', 'AI')

Solution

1. Step 1: Understand bigrams

   Bigrams are pairs of consecutive words in a sentence.

2. Step 2: Extract bigrams from 'I love AI'

   The pairs are ('I', 'love') and ('love', 'AI'). ('I', 'love') shows a correct bigram.

3. Final Answer:

   ('I', 'love') -> Option B

4. Quick Check:

   Bigram = consecutive word pairs = C [OK]

Hint: Bigrams are pairs of consecutive words [OK]

Common Mistakes:

• Including three words instead of two
• Mixing word order in pairs
• Selecting non-consecutive words

3. Given the sentence 'the cat sat on the mat', what is the count of the trigram ('the', 'cat', 'sat')?

medium

A. 0

B. 2

C. 1

D. 3

Solution

1. Step 1: Identify trigrams in the sentence

   Trigrams are sequences of three consecutive words. The trigrams are: ('the', 'cat', 'sat'), ('cat', 'sat', 'on'), ('sat', 'on', 'the'), ('on', 'the', 'mat').

2. Step 2: Count the trigram ('the', 'cat', 'sat')

   This trigram appears once at the start of the sentence.

3. Final Answer:

   1 -> Option C

4. Quick Check:

   Trigram count = 1 [OK]

Hint: Count exact three-word sequences in order [OK]

Common Mistakes:

• Counting non-consecutive words
• Confusing bigrams with trigrams
• Overcounting repeated words

4. Consider this Python code snippet to generate bigrams from a list of words:

words = ['hello', 'world', 'hello']
bigrams = [(words[i], words[i+1]) for i in range(len(words))]

What error will this code produce?

medium

A. No error, code runs correctly

B. SyntaxError: invalid syntax

C. TypeError: unsupported operand type(s)

D. IndexError: list index out of range

Solution

1. Step 1: Analyze the loop range

   The loop runs from 0 to len(words)-1, which is 0 to 2 for 3 words.

2. Step 2: Check index access inside loop

   At i=2, words[i+1] tries to access words[3], which is out of range, causing IndexError.

3. Final Answer:

   IndexError: list index out of range -> Option D

4. Quick Check:

   Loop index exceeds list length = D [OK]

Hint: Check loop range when accessing i+1 index [OK]

Common Mistakes:

• Using full length in range causing out-of-bounds
• Assuming no error without testing
• Confusing syntax errors with runtime errors

5. You want to build a trigram model from a text corpus but notice many rare trigrams cause sparse data issues. Which technique can help improve your model's predictions?

hard

A. Use smoothing methods like Laplace smoothing

B. Increase the n in n-gram to 5-grams

C. Remove all trigrams that appear less than 10 times

D. Ignore the problem and use raw counts

Solution

1. Step 1: Understand sparse data in n-gram models

   Rare trigrams cause zero or low counts, making predictions unreliable.

2. Step 2: Identify smoothing techniques

   Smoothing like Laplace adds small counts to all n-grams, reducing zero probabilities and improving predictions.

3. Final Answer:

   Use smoothing methods like Laplace smoothing -> Option A

4. Quick Check:

   Smoothing reduces sparse data issues = A [OK]

Hint: Apply smoothing to handle rare n-grams [OK]

Common Mistakes:

• Increasing n worsens sparsity
• Removing rare n-grams loses useful info
• Ignoring sparsity leads to poor predictions