Pre-trained embeddings (GloVe) in TensorFlow

Introduction

Pre-trained embeddings like GloVe help computers understand words by turning them into numbers that keep their meaning. This makes teaching machines about language faster and better.

When you want your model to understand word meanings without training from scratch.

When you have limited text data but want good language understanding.

When building chatbots or text classifiers that need to know word relationships.

When you want to improve accuracy quickly by using knowledge learned from large text collections.

Syntax

TensorFlow

embedding_layer = tf.keras.layers.Embedding(
    input_dim=vocab_size,
    output_dim=embedding_dim,
    embeddings_initializer=tf.keras.initializers.Constant(embedding_matrix),
    input_length=max_length,
    trainable=False
)

input_dim is the size of your vocabulary (number of unique words plus one for padding).

output_dim is the size of each word vector (e.g., 50, 100, 200, 300 for GloVe).

Examples

This creates an embedding layer using a 100-dimensional GloVe matrix for a vocabulary of 10,000 words and input sequences of length 50. The embeddings are fixed (not trained).

TensorFlow

embedding_layer = tf.keras.layers.Embedding(
    input_dim=10000,
    output_dim=100,
    embeddings_initializer=tf.keras.initializers.Constant(glove_matrix),
    input_length=50,
    trainable=False
)

Here, the embedding layer uses 300-dimensional GloVe vectors for 5,000 words plus one for padding (total 5001) and input length 100. The embeddings can be updated during training.

TensorFlow

embedding_layer = tf.keras.layers.Embedding(
    input_dim=5001,
    output_dim=300,
    embeddings_initializer=tf.keras.initializers.Constant(glove_matrix),
    input_length=100,
    trainable=True
)

Sample Model

This code creates a small vocabulary and a fake GloVe embedding matrix. It builds an embedding layer using these pre-trained embeddings and applies it to two example sentences represented as word indices. The output shows the shape and the actual embedding vectors for the first sentence.

TensorFlow

import tensorflow as tf
import numpy as np

# Sample vocabulary and GloVe-like embeddings
vocab = ['i', 'love', 'machine', 'learning', 'deep', 'models']
vocab_size = len(vocab) + 1  # +1 for padding
embedding_dim = 50
max_length = 4

# Create a fake GloVe embedding matrix (normally loaded from file)
glove_matrix = np.random.rand(vocab_size, embedding_dim).astype(np.float32)

# Build embedding layer with pre-trained embeddings
embedding_layer = tf.keras.layers.Embedding(
    input_dim=vocab_size,
    output_dim=embedding_dim,
    embeddings_initializer=tf.keras.initializers.Constant(glove_matrix),
    input_length=max_length,
    trainable=False
)

# Sample input: sequences of word indices (batch size 2)
# Words mapped to indices: i=1, love=2, machine=3, learning=4, deep=5, models=6
input_sequences = tf.constant([
    [1, 2, 3, 4],  # "i love machine learning"
    [5, 6, 0, 0]   # "deep models" + padding
])

# Get embeddings for input sequences
embeddings = embedding_layer(input_sequences)

print("Embeddings shape:", embeddings.shape)
print("Embeddings for first sequence (i love machine learning):")
print(embeddings[0].numpy())

Important Notes

Pre-trained embeddings like GloVe are usually loaded from text files and converted into matrices matching your vocabulary.

Setting trainable=False keeps embeddings fixed, which can help when you have little data.

You can set trainable=True to fine-tune embeddings during training for your specific task.

Summary

Pre-trained embeddings turn words into meaningful number vectors using knowledge from large text data.

Use TensorFlow's Embedding layer with a constant initializer to load GloVe embeddings.

Fix embeddings or fine-tune them depending on your data size and task.

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