N-gram language models in NLP - Model Pipeline Trace

Model Pipeline - N-gram language models

An N-gram language model predicts the next word in a sentence by looking at the previous N-1 words. It learns from text data by counting word sequences and uses these counts to guess what comes next.

Data Flow - 6 Stages

1Data in

10000 sentences x variable length→Raw text sentences collected for training→10000 sentences x variable length

"I love machine learning", "The cat sat on the mat"

↓

2Preprocessing

10000 sentences x variable length→Lowercase, remove punctuation, tokenize words→10000 sentences x variable length tokens

["i", "love", "machine", "learning"]

↓

3Feature Engineering

10000 sentences x variable length tokens→Extract N-grams (e.g., bigrams for N=2)→List of N-grams with counts

[('i', 'love'), ('love', 'machine'), ('machine', 'learning')]

↓

4Model Trains

N-gram counts→Calculate probabilities of next word given previous N-1 words→Probability tables for N-grams

P('learning'|'machine') = 0.8

↓

5Metrics Improve

Validation text data→Calculate perplexity to measure model quality→Perplexity score (lower is better)

Perplexity = 120

↓

6Prediction

Previous N-1 words→Use probability tables to predict next word→Next word prediction

Input: 'learning' -> Output: 'is'

Training Trace - Epoch by Epoch

5.0 |*****
4.0 |**** 
3.0 |***  
2.0 |**   
1.0 |*    
    +-----
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	5.0	0.10	Initial model with random-like predictions
2	3.8	0.25	Model starts learning common word sequences
3	2.9	0.40	Better prediction of next words
4	2.3	0.55	Model captures frequent N-grams well
5	1.9	0.65	Converging with improved next word guesses

Prediction Trace - 3 Layers

Layer 1: Input previous words

Layer 2: Look up N-gram probabilities

Layer 3: Select next word

Model Quiz - 3 Questions

What does the N-gram model use to predict the next word?

A The entire sentence

B Random word selection

C The previous N-1 words

D Only the first word

Key Insight

N-gram models learn word patterns by counting sequences and estimating probabilities. As training progresses, the model better predicts the next word, shown by decreasing loss and perplexity. This simple approach captures local word context effectively.

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