Context window handling in NLP - Model Pipeline Trace

Model Pipeline - Context window handling

This pipeline shows how text data is processed in chunks called context windows to help a language model understand and predict words better.

Data Flow - 4 Stages

1Raw Text Input

1 document with 1000 words→Receive full text document→1 document with 1000 words

"The quick brown fox jumps over the lazy dog ..."

↓

2Tokenization

1 document with 1000 words→Split text into tokens (words or subwords)→1 document with 1200 tokens

["The", "quick", "brown", "fox", "jump", "##s", ...]

↓

3Context Windowing

1 document with 1200 tokens→Split tokens into overlapping windows of 100 tokens each→23 windows x 100 tokens

[Window 1: tokens 1-100, Window 2: tokens 51-150, ...]

↓

4Model Input Preparation

23 windows x 100 tokens→Convert tokens to numerical IDs and add special tokens→23 windows x 100 token IDs

[[101, 2003, 2204, ...], [101, 2204, 2024, ...], ...]

Training Trace - Epoch by Epoch

Loss
2.5 |****
2.0 |*** 
1.5 |**  
1.0 |*   
0.5 |    
     +----
      1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.3	0.30	Model starts learning basic word patterns
2	1.8	0.45	Loss decreases as model understands context windows better
3	1.4	0.60	Model improves predictions using overlapping windows
4	1.1	0.70	Context window handling helps capture longer dependencies
5	0.9	0.78	Training converges with good understanding of context

Prediction Trace - 4 Layers

Layer 1: Input Window Selection

Layer 2: Token Embedding Layer

Layer 3: Transformer Layers

Layer 4: Output Layer

Model Quiz - 3 Questions

Why do we split text into overlapping context windows?

A To help the model understand longer text by focusing on smaller parts

B To reduce the number of tokens in the text

C To remove unimportant words from the text

D To make the text shorter for faster reading

Key Insight

Handling text in overlapping context windows helps language models understand longer passages by focusing on smaller, manageable chunks. This improves prediction accuracy as the model learns relationships within each window and across windows.

Practice

1. What does the term context window mean in natural language processing?

easy

A. A method to remove stop words from text

B. The entire document used for training a model

C. A list of all words in a sentence

D. A small part of text around a word used to understand its meaning

Solution

1. Step 1: Understand the definition of context window

   The context window refers to a limited number of words surrounding a target word to help understand its meaning.

2. Step 2: Compare options with the definition

   Only A small part of text around a word used to understand its meaning correctly describes this as a small part of text around a word. Other options describe unrelated concepts.

3. Final Answer:

   A small part of text around a word used to understand its meaning -> Option D

4. Quick Check:

   Context window = small text part around word [OK]

Hint: Context window = nearby words around a target word [OK]

Common Mistakes:

• Confusing context window with entire document
• Thinking it means all words in a sentence
• Mixing it up with stop word removal

2. Which of the following is the correct way to define a context window of size 3 around the word at index 5 in a list words?

easy

A. words[4:7]

B. words[3:8]

C. words[2:7]

D. words[5:8]

Solution

1. Step 1: Understand context window size and indexing

   A window size of 3 means 3 words total, usually centered on the target word. For index 5, the window covers indices 4, 5, 6.

2. Step 2: Check each option's slice range

   words[4:7] slices words[4:7], which includes indices 4, 5, 6 (3 words). Others include wrong ranges or counts.

3. Final Answer:

   words[4:7] -> Option A

4. Quick Check:

   Window size 3 around index 5 = indices 4 to 6 [OK]

Hint: Slice from index-1 to index+2 for window size 3 [OK]

Common Mistakes:

• Using wrong slice indices causing off-by-one errors
• Including too many or too few words
• Not centering window on target word

3. Given the code below, what will be the output?

words = ['I', 'love', 'to', 'eat', 'apples', 'and', 'bananas']
index = 4
window_size = 3
start = max(0, index - window_size // 2)
end = min(len(words), index + window_size // 2 + 1)
context = words[start:end]
print(context)

medium

A. ['to', 'eat', 'apples']

B. ['eat', 'apples', 'and']

C. ['apples', 'and', 'bananas']

D. ['love', 'to', 'eat']

Solution

1. Step 1: Calculate start and end indices

   window_size is 3, so window_size // 2 = 1. start = max(0, 4 - 1) = 3, end = min(7, 4 + 1 + 1) = 6.

2. Step 2: Extract words from start to end

   words[3:6] = ['eat', 'apples', 'and'].

3. Final Answer:

   ['eat', 'apples', 'and'] -> Option B

4. Quick Check:

   Slice words[3:6] = ['eat', 'apples', 'and'] [OK]

Hint: Calculate start/end with floor division and slice accordingly [OK]

Common Mistakes:

• Off-by-one errors in slicing
• Ignoring max/min boundaries
• Misunderstanding integer division

4. The following code tries to get a context window but sometimes throws an error. What is the main issue?

def get_context(words, index, window_size):
    start = index - window_size // 2
    end = index + window_size // 2 + 1
    return words[start:end]

words = ['hello', 'world']
print(get_context(words, 0, 3))

medium

A. index is out of range

B. window_size must be even

C. start can be negative causing an IndexError

D. The function does not return a list

Solution

1. Step 1: Analyze start index calculation

   For index=0 and window_size=3, start = 0 - 1 = -1, which is negative.

2. Step 2: Understand Python slicing with negative start

   Negative start in slicing accesses from the end, which may cause unexpected results or errors if out of range.

3. Final Answer:

   start can be negative causing an IndexError -> Option C

4. Quick Check:

   Negative start index causes slicing issues [OK]

Hint: Check if start index is negative before slicing [OK]

Common Mistakes:

• Assuming negative indices always work safely
• Thinking window_size must be even
• Ignoring index bounds

5. You want to build a model that uses a context window of size 5 to understand words in sentences. Which approach best handles sentences shorter than 5 words without errors?

hard

A. Pad the sentence with special tokens to length 5 before extracting the window

B. Always extract 5 words ignoring sentence length, causing errors if too short

C. Use only the first word as context if sentence is short

D. Skip sentences shorter than 5 words during training

Solution

1. Step 1: Understand the problem with short sentences

   Sentences shorter than the window size cause indexing errors or incomplete context.

2. Step 2: Evaluate options for handling short sentences

   Padding with special tokens ensures fixed length and avoids errors, unlike skipping or ignoring length.

3. Final Answer:

   Pad the sentence with special tokens to length 5 before extracting the window -> Option A

4. Quick Check:

   Padding fixes short sentence context window issues [OK]

Hint: Pad short sentences to window size to avoid errors [OK]

Common Mistakes:

• Ignoring short sentences causing runtime errors
• Skipping data reduces training quality
• Using incomplete context weakens model understanding