Embedding layer usage in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of embedding layer with given input indices

What is the shape of the output tensor after passing the input indices through the embedding layer?

NLP

import torch
import torch.nn as nn

embedding = nn.Embedding(num_embeddings=10, embedding_dim=4)
input_indices = torch.tensor([1, 3, 7, 9])
output = embedding(input_indices)
output_shape = output.shape
print(output_shape)

A torch.Size([1, 4])

B torch.Size([4])

C torch.Size([4, 4])

D torch.Size([10, 4])

💡 Hint

The embedding layer converts each index into a vector of the embedding dimension.

The input tensor has 4 indices, and each index is converted into a vector of size 4, so the output shape is (4, 4).

❓ Model Choice

intermediate

Choosing embedding layer parameters for vocabulary size and embedding dimension

You want to create an embedding layer for a vocabulary of 5000 words, each represented by a 50-dimensional vector. Which is the correct way to initialize this embedding layer in PyTorch?

A nn.Embedding(num_embeddings=50, embedding_dim=5000)

B nn.Embedding(num_embeddings=5000, embedding_dim=50)

C nn.Embedding(num_embeddings=5000, embedding_dim=5000)

D nn.Embedding(num_embeddings=50, embedding_dim=50)

💡 Hint

The first parameter is the vocabulary size, the second is the vector size.

The embedding layer's first argument is the number of unique tokens (vocabulary size), and the second is the size of each embedding vector.

❓ Hyperparameter

advanced

Effect of embedding dimension size on model performance

Increasing the embedding dimension size in a neural network model typically results in which of the following?

A Higher model capacity but increased risk of overfitting

B Lower model capacity and faster training

C No change in model capacity or training time

D Guaranteed better generalization on unseen data

💡 Hint

Think about how larger embeddings affect the number of parameters.

Larger embedding dimensions increase the number of parameters, which can improve capacity but also risk overfitting if not managed.

🔧 Debug

advanced

Identifying error in embedding layer input

What error will this code raise when running the embedding layer with the given input? import torch import torch.nn as nn embedding = nn.Embedding(10, 3) input_indices = torch.tensor([1.0, 2.0, 3.0]) output = embedding(input_indices)

A No error, runs successfully

B TypeError: embedding layer expects a list, not a tensor

C ValueError: embedding dimension mismatch

D RuntimeError: 'input' must be a tensor of dtype torch.int64

💡 Hint

Embedding layers require integer indices, not floats.

Embedding layers require input tensors of integer type (torch.int64). Passing floats causes a runtime error.

🧠 Conceptual

expert

Why use pretrained embeddings instead of training from scratch?

Which of the following is the main advantage of using pretrained word embeddings in a natural language processing model?

A They provide rich semantic information learned from large corpora, improving model performance especially with limited data

B They reduce the model size by compressing the vocabulary

C They eliminate the need for any further training or fine-tuning

D They guarantee 100% accuracy on all NLP tasks

💡 Hint

Think about what pretrained embeddings capture from language data.

Pretrained embeddings capture semantic relationships from large datasets, helping models generalize better when training data is limited.

Practice

1. What is the main purpose of an Embedding layer in NLP models?

easy

A. To split sentences into individual characters

B. To count the number of words in a sentence

C. To convert words into dense vectors that capture meaning

D. To remove stop words from text

Solution

1. Step 1: Understand what embedding layers do

   Embedding layers transform words or tokens into dense numeric vectors that represent semantic meaning.

2. Step 2: Compare options with embedding purpose

   Counting words, removing stop words, or splitting characters are preprocessing steps, not embedding functions.

3. Final Answer:

   To convert words into dense vectors that capture meaning -> Option C

4. Quick Check:

   Embedding = word vectors [OK]

Hint: Embedding layers create numeric word meanings [OK]

Common Mistakes:

• Confusing embedding with tokenization
• Thinking embedding counts words
• Assuming embedding removes words

2. Which of the following is the correct way to create an embedding layer in TensorFlow Keras for 1000 words with 50 dimensions?

easy

A. Embedding(input_dim=1000, output_dim=50)

B. Embedding(output_dim=1000, input_dim=50)

C. Embedding(input_dim=50, output_dim=1000)

D. Embedding(1000, 100)

Solution

1. Step 1: Recall embedding layer parameters

   The first parameter input_dim is vocabulary size (1000), second output_dim is embedding size (50).

2. Step 2: Match parameters to options

   Only Embedding(input_dim=1000, output_dim=50) has the correct parameters: input_dim as vocabulary size (1000) and output_dim as embedding dimension (50). The others either swap these values or use incorrect dimensions.

3. Final Answer:

   Embedding(input_dim=1000, output_dim=50) -> Option A

4. Quick Check:

   input_dim = vocab size, output_dim = vector size [OK]

Hint: input_dim = vocab size, output_dim = vector size [OK]

Common Mistakes:

• Swapping input_dim and output_dim
• Using wrong parameter order
• Confusing embedding size with vocab size

3. Given the code below, what is the shape of the output tensor after the embedding layer?

import tensorflow as tf
embedding = tf.keras.layers.Embedding(input_dim=5000, output_dim=16)
input_seq = tf.constant([[1, 2, 3], [4, 5, 6]])
output = embedding(input_seq)
print(output.shape)

medium

A. (3, 16)

B. (3, 2, 16)

C. (2, 16)

D. (2, 3, 16)

Solution

1. Step 1: Understand input shape

   Input is a 2D tensor with shape (2, 3) representing 2 sequences each of length 3.

2. Step 2: Embedding output shape

   Embedding converts each integer to a 16-dimensional vector, so output shape is (2, 3, 16).

3. Final Answer:

   (2, 3, 16) -> Option D

4. Quick Check:

   Output shape = (batch_size, sequence_length, embedding_dim) [OK]

Hint: Output shape adds embedding dim to input shape [OK]

Common Mistakes:

• Mixing batch and sequence dimensions
• Forgetting embedding dimension in output
• Assuming output shape matches input shape exactly

4. Identify the error in the following embedding layer usage:

embedding = tf.keras.layers.Embedding(input_dim=1000, output_dim=64)
input_seq = tf.constant([[0, 1, 2], [999, 1000, 500]])
output = embedding(input_seq)

medium

A. The input sequence contains an index equal to input_dim, which is invalid

B. The output_dim is too large for the input_dim

C. Embedding layer requires input_dim and output_dim to be equal

D. The input sequence must be a list, not a tensor

Solution

1. Step 1: Check input indices validity

   Embedding indices must be in [0, input_dim-1]. Here, input_dim=1000, so max index is 999.

2. Step 2: Identify invalid index

   Input sequence contains 1000, which is out of range and causes an error.

3. Final Answer:

   The input sequence contains an index equal to input_dim, which is invalid -> Option A

4. Quick Check:

   Indices must be less than input_dim [OK]

Hint: Indices must be less than input_dim [OK]

Common Mistakes:

• Using index equal to input_dim
• Confusing output_dim size limits
• Thinking input must be list, not tensor

5. You want to use an embedding layer for a text classification task with a vocabulary of 10,000 words. You also want to limit the embedding size to 32 to reduce model size. Which approach is best to initialize the embedding layer?

hard

A. Use Embedding(input_dim=10000, output_dim=100) to get richer embeddings

B. Use Embedding(input_dim=10000, output_dim=32) with random initialization and train embeddings

C. Use one-hot encoding instead of embedding for smaller size

D. Use Embedding(input_dim=32, output_dim=10000) to reduce parameters

Solution

1. Step 1: Match embedding size to model constraints

   You want embedding size 32 to keep model small, so output_dim=32 is correct.

2. Step 2: Choose correct input_dim and initialization

   Input_dim must be vocabulary size 10,000. Random initialization is standard and embeddings are trained during model training.

3. Final Answer:

   Use Embedding(input_dim=10000, output_dim=32) with random initialization and train embeddings -> Option B

4. Quick Check:

   Embedding size = output_dim, vocab size = input_dim [OK]

Hint: Match input_dim to vocab, output_dim to embedding size [OK]

Common Mistakes:

• Swapping input_dim and output_dim
• Using one-hot encoding for large vocab
• Choosing embedding size too large for constraints