LSTM for text in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of LSTM layer with return_sequences=True

What is the shape of the output tensor after passing input of shape (32, 10, 50) through an LSTM layer with 64 units and return_sequences=True?

NLP

import tensorflow as tf
input_tensor = tf.random.uniform((32, 10, 50))
lstm_layer = tf.keras.layers.LSTM(64, return_sequences=True)
output = lstm_layer(input_tensor)
print(output.shape)

A (10, 64)

B (32, 64)

C (32, 10, 64)

D (32, 10, 50)

💡 Hint

Remember that return_sequences=True returns output for each time step.

When return_sequences=True, the LSTM returns output for every time step, so the output shape is (batch_size, time_steps, units). Here, batch_size=32, time_steps=10, units=64.

❓ Model Choice

intermediate

Choosing LSTM for text classification

You want to classify movie reviews as positive or negative using their text. Which model architecture is best suited for this task?

A A simple feedforward neural network with bag-of-words input

B An LSTM network processing word sequences

C A convolutional neural network on raw text characters

D A linear regression model on word counts

💡 Hint

Think about models that capture word order and context.

LSTM networks are designed to process sequences and capture context over time, making them well suited for text classification tasks where word order matters.

❓ Hyperparameter

advanced

Effect of increasing LSTM units

What is the most likely effect of increasing the number of units in an LSTM layer from 50 to 200 when training on a small text dataset?

A The model may overfit and training time will increase

B The model will ignore word order

C The model will train faster and generalize better

D The model will underfit due to fewer parameters

💡 Hint

More units mean more parameters to learn.

Increasing units increases model capacity and parameters, which can cause overfitting on small datasets and increase training time.

❓ Metrics

advanced

Evaluating LSTM text model with imbalanced classes

You trained an LSTM model for spam detection on a dataset where 90% of messages are not spam. Which metric is best to evaluate your model's performance?

A Accuracy

B Confusion matrix only

C Mean Squared Error

D Precision and Recall

💡 Hint

Think about metrics that handle class imbalance well.

Accuracy can be misleading with imbalanced data. Precision and recall give better insight into how well the model detects the minority class (spam).

🔧 Debug

expert

Why does this LSTM model not learn?

You trained an LSTM model on text data but the training loss does not decrease. The model code is below. What is the most likely cause?

NLP

import tensorflow as tf
model = tf.keras.Sequential([
    tf.keras.layers.Embedding(input_dim=10000, output_dim=64, input_length=100),
    tf.keras.layers.LSTM(128),
    tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
# Training data: X_train shape (1000, 100), y_train shape (1000,)
model.fit(X_train, y_train, epochs=10, batch_size=32)

A The input sequences are not padded to the same length

B The Embedding layer output_dim is too small

C The model lacks an activation function in the LSTM layer

D The loss function is incorrect for binary classification

💡 Hint

Check the input data shape and preprocessing.

LSTM layers require input sequences to be the same length. If sequences are not padded, the model input shape is inconsistent, causing training issues.

Practice

1. What is the main advantage of using an LSTM model for text data?

easy

A. It converts text directly into images.

B. It removes all punctuation from the text.

C. It remembers the order of words in a sentence.

D. It translates text into multiple languages.

Solution

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

   LSTM models are designed to remember sequences, which means they keep track of word order in sentences.

2. Step 2: Compare options with LSTM function

   Only It remembers the order of words in a sentence. correctly describes LSTM's ability to remember word order. Other options describe unrelated tasks.

3. Final Answer:

   It remembers the order of words in a sentence. -> Option C

4. Quick Check:

   LSTM remembers word order = B [OK]

Hint: LSTM = memory for word order in text [OK]

Common Mistakes:

• Thinking LSTM translates languages
• Confusing LSTM with image processing
• Assuming LSTM removes punctuation

2. Which of the following is the correct way to add an LSTM layer in Keras for text input?

easy

A. model.add(LSTM(128, input_shape=(timesteps, features)))

B. model.add(Dense(128, input_shape=(timesteps, features)))

C. model.add(Conv2D(128, kernel_size=3))

D. model.add(Embedding(128, input_shape=(timesteps, features)))

Solution

1. Step 1: Identify LSTM layer syntax in Keras

   The LSTM layer is added with LSTM(units, input_shape=(timesteps, features)). model.add(LSTM(128, input_shape=(timesteps, features))) matches this syntax.

2. Step 2: Check other options for correctness

   model.add(Dense(128, input_shape=(timesteps, features))) is a Dense layer, not LSTM. model.add(Conv2D(128, kernel_size=3)) is a Conv2D layer for images. model.add(Embedding(128, input_shape=(timesteps, features))) is an Embedding layer, not LSTM.

3. Final Answer:

   model.add(LSTM(128, input_shape=(timesteps, features))) -> Option A

4. Quick Check:

   LSTM layer syntax = D [OK]

Hint: LSTM layer uses LSTM(), not Dense or Conv2D [OK]

Common Mistakes:

• Using Dense instead of LSTM for sequence data
• Confusing Embedding with LSTM layer
• Applying Conv2D for text input

3. Given this code snippet, what will be the shape of the output from the LSTM layer?

model = Sequential()
model.add(Embedding(input_dim=1000, output_dim=64, input_length=10))
model.add(LSTM(32))
output = model.output_shape

medium

A. (None, 10, 32)

B. (None, 32)

C. (None, 64)

D. (10, 32)

Solution

1. Step 1: Understand Embedding and LSTM output shapes

   The Embedding layer outputs (batch_size, 10, 64). The LSTM with 32 units returns (batch_size, 32) by default (last output only).

2. Step 2: Match output shape with options

   (None, 32) matches (None, 32) where None is batch size. Other options are incorrect shapes.

3. Final Answer:

   (None, 32) -> Option B

4. Quick Check:

   LSTM output shape = (None, 32) [OK]

Hint: LSTM returns (batch, units) by default, not sequence [OK]

Common Mistakes:

• Assuming LSTM outputs full sequence by default
• Confusing embedding output with LSTM output
• Ignoring batch size dimension

4. Identify the error in this LSTM model code for text classification:

model = Sequential()
model.add(LSTM(64, input_shape=(100,)))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy')

medium

A. Optimizer 'adam' is not suitable for LSTM models

B. Dense layer activation should be 'relu' for binary classification

C. Loss function should be 'categorical_crossentropy' for binary output

D. Input shape should be 2D, e.g., (timesteps, features), not (100,)

Solution

1. Step 1: Check input shape for LSTM layer

   LSTM expects input shape as (timesteps, features). Here, (100,) is 1D, missing feature dimension.

2. Step 2: Validate other components

   Binary classification uses sigmoid activation and binary_crossentropy loss correctly. Adam optimizer is suitable.

3. Final Answer:

   Input shape should be 2D, e.g., (timesteps, features), not (100,) -> Option D

4. Quick Check:

   LSTM input shape must be 2D = A [OK]

Hint: LSTM input shape needs (timesteps, features) [OK]

Common Mistakes:

• Using 1D input shape for LSTM
• Changing activation incorrectly for binary tasks
• Mixing loss functions for binary classification

5. You want to build an LSTM model to classify movie reviews as positive or negative. Which approach best improves model understanding of word meaning before LSTM processing?

hard

A. Add an Embedding layer to convert words into dense vectors before the LSTM.

B. Use a Dense layer directly on raw text input before LSTM.

C. Apply a Conv2D layer to the text input before LSTM.

D. Skip preprocessing and feed raw text strings directly to LSTM.

Solution

1. Step 1: Understand preprocessing for text in LSTM models

   Embedding layers convert words into meaningful numeric vectors, helping LSTM understand word relationships.

2. Step 2: Evaluate other options

   Dense layers expect numeric input, not raw text. Conv2D is for images. Feeding raw strings to LSTM causes errors.

3. Final Answer:

   Add an Embedding layer to convert words into dense vectors before the LSTM. -> Option A

4. Quick Check:

   Embedding before LSTM = C [OK]

Hint: Use Embedding layer to convert words before LSTM [OK]

Common Mistakes:

• Feeding raw text directly to LSTM
• Using Dense or Conv2D layers on raw text
• Skipping word vector conversion