RNN for text classification in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the right RNN layer for text classification

You want to build a simple recurrent neural network for classifying movie reviews as positive or negative. Which RNN layer is best suited to capture the sequence information while keeping the model simple?

A Use a Conv1D layer because convolution is better for sequence data than RNNs.

B Use a Dense layer directly on the input sequences without any recurrent layers.

C Use a MaxPooling layer to reduce sequence length before classification.

D Use a SimpleRNN layer because it is the most basic recurrent layer and captures sequence order.

💡 Hint

Think about which layer type is designed to handle sequences step-by-step.

SimpleRNN is a recurrent layer designed to process sequences step-by-step, capturing order and dependencies. Conv1D and MaxPooling are not recurrent and Dense layers alone do not handle sequence order.

❓ Predict Output

intermediate

Output shape of RNN layer in text classification model

Consider the following Keras model snippet for text classification:

model = Sequential()
model.add(Embedding(input_dim=10000, output_dim=64, input_length=100))
model.add(SimpleRNN(32))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

print(model.layers[1].output_shape)

What will be printed as the output shape?

A (None, 32)

B (None, 100, 32)

C (None, 64)

D (None, 1)

💡 Hint

SimpleRNN returns the last output by default, not the full sequence.

The SimpleRNN layer with 32 units outputs a vector of size 32 for each input sample. The batch size is None (unspecified), so the output shape is (None, 32).

❓ Hyperparameter

advanced

Choosing the right sequence length for RNN input

You are training an RNN for text classification on movie reviews. Your dataset has reviews of varying lengths, but you must fix the input length for the model. What is the best approach to set the sequence length?

A Set the sequence length to a fixed value like 100, truncating longer reviews and padding shorter ones.

B Set the sequence length to the maximum review length in the dataset to keep all information.

C Set the sequence length to the average review length without padding or truncation.

D Do not fix sequence length; feed variable-length sequences directly to the RNN.

💡 Hint

Think about model input requirements and efficiency.

RNN models require fixed input lengths. Setting a fixed length like 100 and padding/truncating sequences is standard practice to balance information retention and computational efficiency.

❓ Metrics

advanced

Interpreting training metrics for RNN text classifier

After training an RNN text classification model, you observe the following metrics on the validation set:

• Loss: 0.65
• Accuracy: 0.60

What does this tell you about the model's performance?

A The model is performing well with high accuracy and low loss.

B The model has perfect predictions on the validation set.

C The model is underfitting and not learning enough from the data.

D The model is overfitting the training data.

💡 Hint

Consider what accuracy and loss values mean for classification.

An accuracy of 60% and loss of 0.65 on validation is low performance, indicating the model is underfitting and not capturing patterns well.

🔧 Debug

expert

Debugging vanishing gradient in RNN training

You train a SimpleRNN model for text classification but notice the training loss barely decreases after many epochs. Which of the following is the most likely cause?

A The dataset is too large, causing slow training.

B The model suffers from vanishing gradients due to the SimpleRNN architecture.

C The optimizer learning rate is too high, causing divergence.

D The batch size is too small, causing unstable updates.

💡 Hint

Think about common problems with SimpleRNN layers in deep sequence models.

SimpleRNN layers often suffer from vanishing gradients, making it hard to learn long-range dependencies, causing training loss to stagnate.

Practice

1. What is the main reason to use an RNN (Recurrent Neural Network) for text classification tasks?

easy

A. Because RNNs only work with images

B. Because RNNs are faster than other neural networks

C. Because RNNs do not require any training data

D. Because RNNs can remember the order of words and context in sentences

Solution

1. Step 1: Understand RNN's role in text

   RNNs process sequences of words one by one, keeping track of previous words to understand context.

2. Step 2: Identify why order matters

   Text meaning depends on word order, and RNNs remember this order, unlike simple models.

3. Final Answer:

   Because RNNs can remember the order of words and context in sentences -> Option D

4. Quick Check:

   RNN remembers sequence = D [OK]

Hint: RNNs are for sequences and context, not speed or images [OK]

Common Mistakes:

• Thinking RNNs are faster than other models
• Believing RNNs don't need training data
• Confusing RNNs with image-only models

2. Which of the following is the correct way to add a SimpleRNN layer with 32 units in Keras for text classification?

easy

A. model.add(SimpleRNN(32, input_shape=(None, 100)))

B. model.add(SimpleRNN(units=32))

C. model.add(SimpleRNN(32))

D. model.add(SimpleRNN(32, activation='relu'))

Solution

1. Step 1: Recall SimpleRNN syntax

   SimpleRNN requires number of units and input shape for the first layer in a model.

2. Step 2: Check options for correct usage

   model.add(SimpleRNN(32, input_shape=(None, 100))) correctly specifies 32 units and input shape (sequence length unknown, 100 features).

3. Final Answer:

   model.add(SimpleRNN(32, input_shape=(None, 100))) -> Option A

4. Quick Check:

   SimpleRNN needs units and input shape first layer = A [OK]

Hint: First RNN layer needs input_shape, else error [OK]

Common Mistakes:

• Omitting input_shape in first RNN layer
• Using activation='relu' instead of default tanh
• Passing units as keyword incorrectly

3. Given this Keras model snippet for text classification:

model = Sequential()
model.add(Embedding(input_dim=5000, output_dim=16, input_length=10))
model.add(SimpleRNN(8))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

history = model.fit(X_train, y_train, epochs=2, batch_size=32)
print(history.history['accuracy'][-1])

What does history.history['accuracy'][-1] represent?

medium

A. The accuracy of the model on the entire training data after the last epoch

B. The accuracy of the model on the last training batch of the last epoch

C. The loss value of the model after the last epoch

D. The accuracy of the model on the validation data after the last epoch

Solution

1. Step 1: Understand Keras history object

   history.history['accuracy'] stores training accuracy per epoch, so last element is final epoch training accuracy.

2. Step 2: Differentiate training vs batch vs validation

   It is training accuracy on all training data after last epoch, not batch or validation accuracy.

3. Final Answer:

   The accuracy of the model on the entire training data after the last epoch -> Option A

4. Quick Check:

   history.history['accuracy'][-1] = final training accuracy [OK]

Hint: history.history['accuracy'] is training accuracy per epoch [OK]

Common Mistakes:

• Confusing batch accuracy with epoch accuracy
• Mixing loss and accuracy values
• Assuming validation accuracy without validation data

4. You wrote this code to build an RNN model for text classification but get an error:

model = Sequential()
model.add(SimpleRNN(16))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

What is the most likely cause of the error?

medium

A. Dense layer cannot have sigmoid activation

B. SimpleRNN units must be 32 or more

C. Missing input shape for the first SimpleRNN layer

D. Loss function 'binary_crossentropy' is invalid

Solution

1. Step 1: Check first layer requirements

   The first RNN layer must know input shape to accept data; missing input_shape causes error.

2. Step 2: Validate other options

   Sigmoid activation in Dense is valid for binary classification; units can be any positive integer; binary_crossentropy is valid loss.

3. Final Answer:

   Missing input shape for the first SimpleRNN layer -> Option C

4. Quick Check:

   First RNN layer needs input_shape = B [OK]

Hint: Always set input_shape in first RNN layer to avoid errors [OK]

Common Mistakes:

• Assuming activation or loss function causes error
• Thinking units must be 32 or more
• Ignoring input shape requirement

5. You want to improve your RNN text classifier by adding an Embedding layer before the SimpleRNN. Which of these changes is correct and why?

Original:
model = Sequential()
model.add(SimpleRNN(16, input_shape=(10, 100)))
model.add(Dense(1, activation='sigmoid'))

Change:
model = Sequential()
model.add(Embedding(input_dim=5000, output_dim=100, input_length=10))
model.add(SimpleRNN(16))
model.add(Dense(1, activation='sigmoid'))

hard

A. Incorrect: Embedding output_dim must match SimpleRNN units

B. Correct: Embedding converts word indices to vectors, so SimpleRNN input shape changes automatically

C. Incorrect: Embedding layer should come after SimpleRNN

D. Incorrect: Embedding layer requires activation='relu'

Solution

1. Step 1: Understand Embedding role

   Embedding layer converts integer word indices into dense vectors, preparing input for RNN.

2. Step 2: Check model order and shapes

   Embedding outputs shape (batch, sequence_length, output_dim), matching SimpleRNN expected input shape, so no input_shape needed in SimpleRNN.

3. Final Answer:

   Correct: Embedding converts word indices to vectors, so SimpleRNN input shape changes automatically -> Option B

4. Quick Check:

   Embedding before RNN changes input shape correctly = C [OK]

Hint: Embedding layer must come before RNN to convert words to vectors [OK]

Common Mistakes:

• Placing Embedding after RNN
• Matching output_dim to RNN units incorrectly
• Adding activation to Embedding layer