Why Self-attention and multi-head attention in NLP? - Purpose & Use Cases

The Big Idea

What if a machine could instantly grasp every important detail in a long story, just like you do when you pay close attention?

The Scenario

Imagine trying to understand a long story by reading each sentence one by one and remembering everything yourself. You have to keep track of all the important details and how they connect, but your memory can only hold so much at once.

The Problem

Doing this manually is slow and easy to mess up. You might forget key parts or misunderstand how different pieces relate. It's like trying to juggle many balls at once--your brain gets overwhelmed and mistakes happen.

The Solution

Self-attention helps by letting the model look at all parts of the story at the same time and decide which parts are important to focus on. Multi-head attention takes this further by looking from different perspectives simultaneously, capturing more details and connections.

Before vs After

✗ Before

for word in sentence:
    context = remember_previous_words()
    process(word, context)

✓ After

attention_scores = self_attention(words)
multi_view = multi_head_attention(attention_scores)

What It Enables

This lets machines understand language deeply and quickly, making tasks like translation, summarizing, and answering questions much better.

Real Life Example

When you use a voice assistant to ask a question, self-attention and multi-head attention help it understand your words in context, so it gives you the right answer even if your sentence is long or complex.

Key Takeaways

Manual understanding of long text is slow and error-prone.

Self-attention lets models focus on important parts of input all at once.

Multi-head attention captures different views for richer understanding.

Practice

1. What is the main purpose of self-attention in natural language processing?

easy

A. To reduce the size of the input data by removing words

B. To generate random sentences without context

C. To translate text from one language to another

D. To let the model focus on important words by comparing all words to each other

Solution

1. Step 1: Understand self-attention's role

   Self-attention helps the model look at all words in a sentence and decide which ones are important by comparing them to each other.

2. Step 2: Match purpose with options

   To let the model focus on important words by comparing all words to each other correctly describes this focus mechanism, while others describe unrelated tasks.

3. Final Answer:

   To let the model focus on important words by comparing all words to each other -> Option D

4. Quick Check:

   Self-attention = focus on important words [OK]

Hint: Self-attention means comparing words to find importance [OK]

Common Mistakes:

• Confusing self-attention with translation
• Thinking self-attention removes words
• Assuming it generates random text

2. Which of the following is the correct way to describe multi-head attention?

easy

A. Running several self-attention processes in parallel to get richer understanding

B. Applying self-attention only once on the input

C. Using attention only on the first word of a sentence

D. Ignoring word relationships and focusing on word order only

Solution

1. Step 1: Recall multi-head attention definition

   Multi-head attention means running multiple self-attention operations at the same time to capture different aspects of word relationships.

2. Step 2: Compare options to definition

   Running several self-attention processes in parallel to get richer understanding matches this exactly; others describe incomplete or incorrect ideas.

3. Final Answer:

   Running several self-attention processes in parallel to get richer understanding -> Option A

4. Quick Check:

   Multi-head attention = multiple self-attentions [OK]

Hint: Multi-head means many self-attentions at once [OK]

Common Mistakes:

• Thinking multi-head means single attention
• Believing it focuses only on first word
• Ignoring word relationships

3. Given the following simplified self-attention scores matrix for a 3-word sentence:
Scores = [[1, 0.5, 0], [0.5, 1, 0.2], [0, 0.2, 1]]
What is the attention weight for the second word attending to the third word after applying softmax on its row?

medium

A. Approximately 0.21

B. Approximately 0.50

C. Approximately 0.29

D. Approximately 0.70

Solution

1. Step 1: Extract the second row scores

   The second word's scores are [0.5, 1, 0.2].

2. Step 2: Apply softmax to these scores

   Softmax formula: exp(score) / sum(exp(all scores)). Calculate exp(0.5)=1.65, exp(1)=2.72, exp(0.2)=1.22. Sum = 1.65+2.72+1.22=5.59. Attention weight for third word = 1.22/5.59 ≈ 0.218.

3. Final Answer:

   Approximately 0.21 -> Option A

4. Quick Check:

   Softmax normalizes scores to probabilities [OK]

Hint: Softmax turns scores into probabilities summing to 1 [OK]

Common Mistakes:

• Forgetting to exponentiate scores
• Dividing by wrong sum
• Mixing row and column values

4. Consider this Python code snippet for multi-head attention weights calculation:

import numpy as np

def multi_head_attention(scores_list):
    heads = []
    for scores in scores_list:
        weights = np.exp(scores) / np.sum(np.exp(scores))
        heads.append(weights)
    return np.mean(heads, axis=0)

scores_list = [np.array([1, 0, 2]), np.array([0, 1, 1])]
print(multi_head_attention(scores_list))

What is the main bug in this code?

medium

A. Softmax is applied incorrectly; denominator should sum over exp(scores) per head

B. The function returns mean of weights instead of concatenating heads

C. The code uses np.exp twice causing overflow

D. Scores_list should be a 2D array, not a list of arrays

Solution

1. Step 1: Analyze softmax calculation

   Softmax is correctly applied per head by dividing exp(scores) by sum of exp(scores).

2. Step 2: Check output aggregation

   The function averages the weights from each head, but multi-head attention should concatenate or combine heads differently, not average weights element-wise.

3. Final Answer:

   The function returns mean of weights instead of concatenating heads -> Option B

4. Quick Check:

   Multi-head attention combines heads, not averages weights [OK]

Hint: Multi-head attention concatenates heads, not averages weights [OK]

Common Mistakes:

• Thinking averaging weights is correct
• Confusing softmax denominator
• Assuming input format is wrong

5. You want to improve a Transformer model's ability to understand complex sentences by increasing the number of attention heads from 4 to 8. What is the most likely effect of this change?

hard

A. The model will ignore word order completely

B. The model will run faster but lose accuracy

C. The model can capture more diverse word relationships but may require more computation

D. The model will only focus on the first half of the sentence

Solution

1. Step 1: Understand effect of increasing attention heads

   More heads mean the model can look at different parts of the sentence simultaneously, capturing richer relationships.

2. Step 2: Consider computational cost and accuracy

   Increasing heads usually increases computation and memory needs but can improve understanding and accuracy.

3. Final Answer:

   The model can capture more diverse word relationships but may require more computation -> Option C

4. Quick Check:

   More heads = richer focus + more compute [OK]

Hint: More heads = better focus but slower model [OK]

Common Mistakes:

• Assuming more heads always make model faster
• Thinking word order is ignored
• Believing model focuses only on part of sentence