Self-attention and multi-head attention in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to compute the attention scores by multiplying queries and keys.

NLP

attention_scores = torch.matmul(queries, [1].transpose(-2, -1))

Drag options to blanks, or click blank then click option'

Aqueries

Bkeys

Cvalues

Dweights

Attempts:

3 left

💡 Hint

Common Mistakes

Using values instead of keys for multiplication.

Not transposing the keys before multiplication.

In self-attention, attention scores are computed by multiplying queries with the transpose of keys.

2fill in blank

medium

Complete the code to scale the attention scores by the square root of the key dimension.

NLP

scaled_scores = attention_scores / math.sqrt([1])

Drag options to blanks, or click blank then click option'

Avalue_dim

Bbatch_size

Ckey_dim

Dquery_dim

Attempts:

3 left

💡 Hint

Common Mistakes

Scaling by query dimension instead of key dimension.

Forgetting to scale attention scores.

Attention scores are scaled by the square root of the key dimension to stabilize gradients.

3fill in blank

hard

Fix the error in applying softmax to the attention scores along the correct dimension.

NLP

attention_weights = torch.nn.functional.softmax(attention_scores, dim=[1])

Drag options to blanks, or click blank then click option'

A-1

B1

C0

D-2

Attempts:

3 left

💡 Hint

Common Mistakes

Applying softmax along batch or query dimension.

Using dim=1 which is usually the sequence length dimension but not keys.

Softmax should be applied along the last dimension (keys dimension) to get proper attention weights.

4fill in blank

hard

Fill both blanks to compute multi-head attention output by concatenating heads and applying a linear layer.

NLP

multihead_output = self.linear_out(torch.cat([1], dim=[2]))

Drag options to blanks, or click blank then click option'

Aattended_heads

B1

C-1

Dheads

Attempts:

3 left

💡 Hint

Common Mistakes

Concatenating along the batch dimension.

Using wrong variable name for attended heads.

Multi-head outputs are concatenated along the last dimension before passing through a linear layer.

5fill in blank

hard

Fill all three blanks to implement scaled dot-product attention: compute scores, apply softmax, and multiply by values.

NLP

scores = torch.matmul(queries, [1].transpose(-2, -1)) / math.sqrt([2])
weights = torch.nn.functional.softmax(scores, dim=[3])
output = torch.matmul(weights, values)

Drag options to blanks, or click blank then click option'

Akeys

Bkey_dim

C-1

Dqueries

Attempts:

3 left

💡 Hint

Common Mistakes

Using values instead of keys for scores.

Applying softmax along wrong dimension.

Forgetting to scale scores.

Scaled dot-product attention multiplies queries by keys, scales by sqrt of key dimension, applies softmax along last dimension, then multiplies by values.

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