Pre-trained embeddings (GloVe) in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the GloVe embeddings file.

TensorFlow

embedding_index = {}
with open('glove.6B.100d.txt', encoding='utf8') as f:
    for line in f:
        values = line.split()
        word = values[[1]]
        coefs = np.asarray(values[1:], dtype='float32')
        embedding_index[word] = coefs

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

A0

B1

C-1

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using index 1 instead of 0 for the word.

Using negative index which refers to the last element.

The first value in each line is the word itself, so we use index 0 to get the word.

2fill in blank

medium

Complete the code to create an embedding matrix for the tokenizer's word index.

TensorFlow

embedding_dim = 100
embedding_matrix = np.zeros((len(word_index) + 1, embedding_dim))
for word, i in word_index.items():
    embedding_vector = embedding_index.get(word)
    if embedding_vector is not None:
        embedding_matrix[i] = [1]

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

Aword

Bi

Cembedding_index

Dembedding_vector

Attempts:

3 left

💡 Hint

Common Mistakes

Assigning the word string instead of the vector.

Assigning the index instead of the vector.

We assign the embedding vector for the word to the corresponding row in the matrix.

3fill in blank

hard

Fix the error in the code to create a Keras Embedding layer using the pre-trained embedding matrix.

TensorFlow

embedding_layer = tf.keras.layers.Embedding(
    input_dim=embedding_matrix.shape[0],
    output_dim=embedding_matrix.shape[1],
    weights=[[1]],
    trainable=False
)

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

Aword_index

Bembedding_index

Cembedding_matrix

Dembedding_vector

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the embedding_index dictionary instead of the matrix.

Passing a single vector instead of a list containing the matrix.

The weights argument expects a list containing the embedding matrix.

4fill in blank

hard

Fill both blanks to compile the model with an optimizer and loss function suitable for binary classification.

TensorFlow

model.compile(optimizer=[1], loss=[2], metrics=['accuracy'])

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

A'adam'

B'binary_crossentropy'

C'categorical_crossentropy'

D'sgd'

Attempts:

3 left

💡 Hint

Common Mistakes

Using categorical_crossentropy for binary classification.

Using SGD optimizer without tuning.

Adam optimizer and binary_crossentropy loss are standard choices for binary classification tasks.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps words to their embedding vectors only if the word length is greater than 3.

TensorFlow

filtered_embeddings = {word: embedding_index[word] for word in embedding_index if [1] [2] [3]

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

Alen(word)

B>

C3

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using word instead of len(word).

Using less than operator instead of greater than.

We check if the length of the word is greater than 3 to filter embeddings.

Practice

1. What is the main purpose of using pre-trained GloVe embeddings in TensorFlow models?

easy

A. To convert words into meaningful number vectors using prior knowledge

B. To generate random numbers for model initialization

C. To increase the size of the training dataset

D. To replace the output layer of the model

Solution

1. Step 1: Understand what embeddings do

   Embeddings convert words into vectors that capture meaning from large text data.

2. Step 2: Identify the role of pre-trained GloVe embeddings

   GloVe embeddings provide these vectors based on prior training on big text corpora, helping models understand word meanings without training from scratch.

3. Final Answer:

   To convert words into meaningful number vectors using prior knowledge -> Option A

4. Quick Check:

   Pre-trained embeddings = meaningful word vectors [OK]

Hint: Pre-trained embeddings map words to vectors using learned knowledge [OK]

Common Mistakes:

• Thinking embeddings generate random numbers
• Confusing embeddings with dataset size
• Assuming embeddings replace output layers

2. Which TensorFlow code snippet correctly loads GloVe embeddings into an Embedding layer with fixed weights?

easy

A. embedding_layer = tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim, embeddings_initializer=tf.keras.initializers.Constant(glove_matrix), trainable=False)

B. embedding_layer = tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim, embeddings_initializer='random_uniform', trainable=True)

C. embedding_layer = tf.keras.layers.Dense(units=embedding_dim, activation='relu')

D. embedding_layer = tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim, embeddings_initializer=tf.keras.initializers.RandomNormal(), trainable=False)

Solution

1. Step 1: Identify correct Embedding layer usage for GloVe

   We use Embedding layer with embeddings_initializer set to Constant(glove_matrix) to load pre-trained weights.

2. Step 2: Check trainable flag for fixed embeddings

   Setting trainable=False ensures embeddings are not updated during training, which matches the question.

3. Final Answer:

   embedding_layer = tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim, embeddings_initializer=tf.keras.initializers.Constant(glove_matrix), trainable=False) -> Option A

4. Quick Check:

   Constant initializer + trainable=False = fixed GloVe embeddings [OK]

Hint: Use Constant initializer and trainable=False for fixed GloVe embeddings [OK]

Common Mistakes:

• Using random initializers instead of Constant
• Setting trainable=True when embeddings should be fixed
• Using Dense layer instead of Embedding

3. Given the code below, what will be the shape of embedding_output?

embedding_layer = tf.keras.layers.Embedding(input_dim=10000, output_dim=50, embeddings_initializer=tf.keras.initializers.Constant(glove_matrix), trainable=False)
input_seq = tf.constant([[1, 5, 10], [2, 3, 4]])
embedding_output = embedding_layer(input_seq)

medium

A. (2, 50)

B. (3, 2, 50)

C. (2, 3, 50)

D. (3, 50)

Solution

1. Step 1: Analyze input sequence shape

   Input sequence has shape (2, 3) because it has 2 sequences each with 3 tokens.

2. Step 2: Understand Embedding output shape

   Embedding layer converts each token to a 50-dimensional vector, so output shape is (2, 3, 50).

3. Final Answer:

   (2, 3, 50) -> Option C

4. Quick Check:

   Input shape (2,3) + embedding_dim 50 = (2,3,50) [OK]

Hint: Embedding output shape = input shape + embedding dimension [OK]

Common Mistakes:

• Swapping batch and sequence dimensions
• Forgetting embedding dimension in output shape
• Assuming output shape is 2D instead of 3D

4. Identify the error in this code snippet that loads GloVe embeddings:

embedding_layer = tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim, embeddings_initializer=tf.keras.initializers.Constant(glove_matrix))
embedding_layer.trainable = False
model = tf.keras.Sequential([embedding_layer, tf.keras.layers.Dense(10)])

medium

A. Dense layer cannot follow an Embedding layer

B. Using Constant initializer is incorrect for GloVe embeddings

C. Embedding layer must be the last layer in the model

D. Setting trainable attribute after layer creation does not freeze embeddings

Solution

1. Step 1: Check how to freeze embeddings

   Setting trainable=False must be done during layer creation, not by assigning attribute later.

2. Step 2: Understand effect of late trainable assignment

   Assigning embedding_layer.trainable = False after creation does not properly freeze weights in Keras models.

3. Final Answer:

   Setting trainable attribute after layer creation does not freeze embeddings -> Option D

4. Quick Check:

   Freeze embeddings by trainable=False in constructor [OK]

Hint: Set trainable=False when creating Embedding layer to freeze weights [OK]

Common Mistakes:

• Setting trainable attribute after layer creation
• Thinking Constant initializer is wrong for GloVe
• Believing Embedding must be last layer

5. You want to fine-tune GloVe embeddings on a small dataset. Which approach is best to avoid overfitting while still improving embeddings?

hard

A. Randomly initialize embeddings and keep trainable=False

B. Initialize Embedding layer with GloVe weights, set trainable=True, and use dropout after embeddings

C. Use GloVe embeddings with trainable=False and no dropout

D. Freeze embeddings and add many Dense layers without regularization

Solution

1. Step 1: Understand fine-tuning embeddings on small data

   Fine-tuning means allowing embeddings to update (trainable=True) but small data risks overfitting.

2. Step 2: Use dropout to reduce overfitting

   Applying dropout after embeddings helps regularize and prevent overfitting during fine-tuning.

3. Final Answer:

   Initialize Embedding layer with GloVe weights, set trainable=True, and use dropout after embeddings -> Option B

4. Quick Check:

   Fine-tune + dropout = better small data training [OK]

Hint: Fine-tune with trainable=True plus dropout to avoid overfitting [OK]

Common Mistakes:

• Freezing embeddings when fine-tuning is needed
• Skipping dropout causing overfitting
• Random initialization losing pre-trained knowledge