Attention mechanism basics in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to compute the attention scores using dot product.

NLP

attention_scores = query [1] key.transpose(-2, -1)

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

A@

B+

C*

D-

Attempts:

3 left

💡 Hint

Common Mistakes

Using '*' which does element-wise multiplication, not matrix multiplication.

Using '+' or '-' which are arithmetic operators not for multiplication.

The attention scores are computed by the dot product of the query and the key vectors. In Python, the '@' operator performs matrix multiplication.

2fill in blank

medium

Complete the code to apply softmax to the attention scores along the last dimension.

NLP

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

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

A0

B1

C2

D-1

Attempts:

3 left

💡 Hint

Common Mistakes

Applying softmax along the wrong dimension, which changes the meaning of weights.

Using 0 or 1 which may not correspond to the keys dimension.

Softmax is applied along the last dimension (-1) to convert scores into probabilities for each key.

3fill in blank

hard

Fix the error in scaling the attention scores by the square root of the key dimension.

NLP

scaled_scores = attention_scores / torch.sqrt(torch.tensor([1], dtype=torch.float32))

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

Akey.shape[0]

Bkey.size(-1)

Cquery.size(0)

Dquery.shape[1]

Attempts:

3 left

💡 Hint

Common Mistakes

Using batch size or query dimensions instead of key vector dimension.

Using shape[0] which is usually batch size, not feature size.

The scaling factor is the square root of the key vector dimension, which is the last dimension size of the key tensor.

4fill in blank

hard

Fill both blanks to compute the attention output by multiplying attention weights with values.

NLP

attention_output = torch.matmul([1], [2])

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

Aattention_weights

Bvalues

Cquery

Dkey

Attempts:

3 left

💡 Hint

Common Mistakes

Multiplying query or key instead of values.

Swapping the order of multiplication.

The attention output is the weighted sum of the value vectors, so we multiply attention weights by values.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each word to its length if length is greater than 3.

NLP

lengths = { [1] : [2] for [3] in words if len([3]) > 3 }

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

Aword

Blen(word)

Ditem

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong variable name in the loop.

Using the word as value instead of its length.

This dictionary comprehension creates a mapping from each word to its length, but only for words longer than 3 characters.

Practice

1. What is the main purpose of the attention mechanism in NLP models?

easy

A. To reduce the number of layers in the model

B. To focus on important parts of the input data

C. To increase the size of the input data

D. To randomly shuffle the input tokens

Solution

1. Step 1: Understand the role of attention

   Attention helps the model decide which parts of the input are important to look at when making predictions.

2. Step 2: Compare options with the concept

   Only To focus on important parts of the input data correctly describes this focus on important input parts.

3. Final Answer:

   To focus on important parts of the input data -> Option B

4. Quick Check:

   Attention = Focus on important input [OK]

Hint: Attention means focusing on key input parts [OK]

Common Mistakes:

• Thinking attention increases input size
• Confusing attention with model depth
• Assuming attention shuffles data

2. Which of the following correctly represents the formula to compute attention weights using query (Q) and key (K) vectors?

easy

A. Sigmoid(Q - K)

B. Softmax(Q + K)

C. ReLU(Q x K)

D. Softmax(Q x K^T)

Solution

1. Step 1: Recall attention weight calculation

   Attention weights are computed by taking the dot product of query and key vectors, then applying softmax.

2. Step 2: Match formula to options

   Softmax(Q x K^T) shows softmax applied to Q multiplied by the transpose of K, which is correct.

3. Final Answer:

   Softmax(Q x K^T) -> Option D

4. Quick Check:

   Attention weights = softmax(dot product) [OK]

Hint: Attention weights = softmax of query-key dot product [OK]

Common Mistakes:

• Adding Q and K instead of dot product
• Using ReLU or Sigmoid instead of softmax
• Ignoring transpose on key vector

3. Given query vector Q = [1, 0], key vectors K1 = [1, 0], K2 = [0, 1], and value vectors V1 = [10, 0], V2 = [0, 20], what is the attention output after applying softmax on Q·K^T and multiplying by values?

medium

A. [10, 0]

B. [5, 10]

C. [7.31, 5.38]

D. [0, 20]

Solution

1. Step 1: Calculate dot products Q·K1 and Q·K2

   Q·K1 = 1*1 + 0*0 = 1; Q·K2 = 1*0 + 0*1 = 0.

2. Step 2: Apply softmax to [1, 0]

   Softmax(1,0) = [e^1/(e^1+e^0), e^0/(e^1+e^0)] ≈ [0.731, 0.269].

3. Step 3: Multiply weights by values and sum

   Output = 0.731*[10,0] + 0.269*[0,20] = [7.31, 0] + [0,5.38] = [7.31, 5.38].

4. Step 4: Match to options

   The computed output [7.31, 5.38] matches [7.31, 5.38] (approximate values).

5. Final Answer:

   [7.31, 5.38] -> Option C

6. Quick Check:

   Softmax weights x values = output [OK]

Hint: Softmax weights times values gives attention output [OK]

Common Mistakes:

• Skipping softmax normalization
• Multiplying query with values directly
• Ignoring vector multiplication order

4. Identify the error in this attention weight calculation code snippet:

import numpy as np
Q = np.array([1, 2])
K = np.array([[1, 0], [0, 1]])
scores = np.dot(Q, K)
weights = np.exp(scores) / np.sum(np.exp(scores))

medium

A. Dot product should be between Q and K transpose

B. Softmax calculation is incorrect

C. Q and K should be swapped in dot product

D. No error, code is correct

Solution

1. Step 1: Check dot product dimensions

   Q is shape (2,), K is (2,2). np.dot(Q, K) results in shape (2,), but attention needs dot product with K transpose.

2. Step 2: Correct dot product usage

   Dot product should be np.dot(Q, K.T) to get scores for each key vector.

3. Final Answer:

   Dot product should be between Q and K transpose -> Option A

4. Quick Check:

   Dot product with K transpose needed [OK]

Hint: Dot product query with key transpose for scores [OK]

Common Mistakes:

• Using K instead of K transpose
• Miscomputing softmax manually
• Swapping Q and K incorrectly

5. In a transformer model, why is scaling the dot product by the square root of the key dimension important before applying softmax?

hard

A. To prevent large dot product values causing softmax to produce very small gradients

B. To increase the dot product values for better attention

C. To normalize the query vectors only

D. To reduce the number of keys processed

Solution

1. Step 1: Understand dot product scaling

   Without scaling, large dot product values can make softmax outputs very close to 0 or 1, causing gradients to vanish during training.

2. Step 2: Purpose of scaling by sqrt of key dimension

   Scaling reduces the magnitude of dot products, keeping softmax outputs more balanced and gradients healthy.

3. Final Answer:

   To prevent large dot product values causing softmax to produce very small gradients -> Option A

4. Quick Check:

   Scaling avoids gradient vanishing in softmax [OK]

Hint: Scale dot product to keep softmax gradients stable [OK]

Common Mistakes:

• Thinking scaling increases dot product values
• Believing scaling normalizes queries only
• Assuming scaling reduces keys processed