Bidirectional LSTM in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a Bidirectional LSTM?

A Bidirectional LSTM is a type of neural network that reads data in two directions: forward and backward. This helps it understand context from both past and future in a sequence.

beginner

Why use Bidirectional LSTM instead of a regular LSTM?

Because it looks at the sequence from both directions, it can capture more context and improve understanding, especially in language tasks where future words help understand the current word.

intermediate

How does a Bidirectional LSTM process input sequences?

It has two LSTM layers: one processes the sequence from start to end, the other from end to start. Their outputs are combined to form a richer representation.

beginner

What are common applications of Bidirectional LSTMs?

They are used in tasks like speech recognition, language translation, and text classification where understanding context from both past and future words is important.

intermediate

How do you combine outputs from forward and backward LSTMs in a Bidirectional LSTM?

The outputs can be concatenated, added, or averaged to create a single output vector that contains information from both directions.

What does a Bidirectional LSTM do differently from a standard LSTM?

A Only processes data backward

B Uses convolutional layers instead of recurrent layers

C Processes data in both forward and backward directions

D Does not use gates

A Bidirectional LSTM processes sequences in both forward and backward directions to capture context from past and future.

Why is context from future words useful in language tasks?

A It helps understand the meaning of current words better

B It speeds up training

C It reduces the size of the model

D It prevents overfitting

Knowing future words helps the model understand the current word's meaning more accurately.

How are outputs from forward and backward LSTMs usually combined?

A Ignoring one direction

B Multiplying weights only

C Using only the forward output

D Concatenation, addition, or averaging

Outputs from both directions are combined by concatenation, addition, or averaging to form a richer representation.

Which of these is NOT a typical use case for Bidirectional LSTMs?

A Image classification

B Speech recognition

C Language translation

D Text classification

Bidirectional LSTMs are mainly used for sequence data like text or speech, not for image classification.

What type of neural network is an LSTM?

A Convolutional Neural Network

B Recurrent Neural Network

C Feedforward Neural Network

D Generative Adversarial Network

LSTM is a type of Recurrent Neural Network designed to handle sequences and remember long-term dependencies.

Explain how a Bidirectional LSTM processes a sentence and why this is helpful.

Think about reading a sentence from left to right and right to left.

Describe a real-life example where using a Bidirectional LSTM would improve results compared to a regular LSTM.

Consider how knowing the next word in a sentence helps understand the current word.

Practice

1. What is the main advantage of using a Bidirectional LSTM compared to a standard LSTM?

easy

A. It only reads the sequence backward for better performance.

B. It uses fewer parameters, making the model faster to train.

C. It processes the input sequence in both forward and backward directions to capture more context.

D. It replaces LSTM cells with simpler RNN cells.

Solution

1. Step 1: Understand LSTM directionality

   A standard LSTM reads the input sequence only in the forward direction, from start to end.

2. Step 2: Analyze Bidirectional LSTM behavior

   A Bidirectional LSTM reads the sequence both forward and backward, capturing information from past and future context.

3. Final Answer:

   It processes the input sequence in both forward and backward directions to capture more context. -> Option C

4. Quick Check:

   Bidirectional means forward + backward = C [OK]

Hint: Bidirectional means reading sequence both ways [OK]

Common Mistakes:

• Thinking it only reads backward
• Assuming it reduces parameters
• Confusing it with simpler RNNs

2. Which of the following is the correct way to add a Bidirectional LSTM layer in Keras?

easy

A. model.add(Bidirectional(LSTM(units=64)))

B. model.add(LSTM(Bidirectional(units=64)))

C. model.add(Bidirectional(units=64, LSTM()))

D. model.add(LSTM(units=64, bidirectional=True))

Solution

1. Step 1: Recall Keras Bidirectional syntax

   In Keras, the Bidirectional wrapper takes an RNN layer like LSTM as its argument.

2. Step 2: Check each option

   model.add(Bidirectional(LSTM(units=64))) correctly wraps LSTM inside Bidirectional. The other options misuse the syntax or parameters.

3. Final Answer:

   model.add(Bidirectional(LSTM(units=64))) -> Option A

4. Quick Check:

   Bidirectional wraps LSTM layer = A [OK]

Hint: Bidirectional wraps LSTM layer, not the other way [OK]

Common Mistakes:

• Putting Bidirectional inside LSTM
• Passing units to Bidirectional instead of LSTM
• Using bidirectional=True parameter in LSTM

3. Consider this code snippet using TensorFlow Keras:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Bidirectional, Dense

model = Sequential()
model.add(Bidirectional(LSTM(10, return_sequences=False), input_shape=(5, 8)))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy')

import numpy as np
x = np.random.random((2, 5, 8))
pred = model.predict(x)
print(pred.shape)

What will be the shape of pred?

medium

A. (2, 10)

B. (2, 1)

C. (5, 1)

D. (2, 20)

Solution

1. Step 1: Understand model output shape

   The Bidirectional LSTM with 10 units outputs 20 features (10 forward + 10 backward) per timestep. Since return_sequences=False, it outputs only the last timestep's features, shape (batch_size, 20).

2. Step 2: Dense layer output shape

   The Dense layer with 1 unit outputs shape (batch_size, 1). Input batch size is 2, so output shape is (2, 1).

3. Final Answer:

   (2, 1) -> Option B

4. Quick Check:

   Batch size 2, Dense 1 unit = (2, 1) [OK]

Hint: Dense(1) outputs shape (batch_size, 1) [OK]

Common Mistakes:

• Confusing return_sequences=True vs False
• Forgetting bidirectional doubles units
• Mixing batch and timestep dimensions

4. You wrote this code but get an error:

model = Sequential()
model.add(Bidirectional(LSTM(32), input_shape=(10, 16)))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')

# Training data
X_train = np.random.random((100, 10, 16))
y_train = np.random.random((100,))

model.fit(X_train, y_train, epochs=5)

The error says: ValueError: Error when checking target: expected dense_1 to have shape (None, 1) but got array with shape (100,)
What is the fix?

medium

A. Change Dense layer units to 100.

B. Remove Bidirectional wrapper.

C. Set return_sequences=True in LSTM layer.

D. Change y_train shape to (100, 1) by reshaping it.

Solution

1. Step 1: Understand error message

   The model expects targets with shape (batch_size, 1) because Dense(1) outputs shape (None, 1). But y_train has shape (100,), missing the last dimension.

2. Step 2: Fix target shape

   Reshape y_train to (100, 1) to match model output shape. This fixes the mismatch error.

3. Final Answer:

   Change y_train shape to (100, 1) by reshaping it. -> Option D

4. Quick Check:

   Target shape matches output shape = B [OK]

Hint: Targets must match model output shape exactly [OK]

Common Mistakes:

• Changing model output units instead of target shape
• Setting return_sequences=True unnecessarily
• Removing Bidirectional without reason

5. You want to build a sentiment analysis model using a Bidirectional LSTM on text sequences of length 100. Which of these model designs best captures full context and outputs a fixed-size vector for classification?

hard

A. Embedding -> Bidirectional(LSTM with return_sequences=True) -> GlobalMaxPooling1D -> Dense

B. Embedding -> Bidirectional(LSTM with return_sequences=False) -> Dense

C. Embedding -> LSTM with return_sequences=False -> Dense

D. Embedding -> Bidirectional(LSTM with return_sequences=True) -> Dense

Solution

1. Step 1: Understand context capture

   Bidirectional LSTM reads sequences forward and backward, capturing full context.

2. Step 2: Fixed-size vector output

   Using return_sequences=True outputs a sequence, so applying GlobalMaxPooling1D converts it to a fixed-size vector summarizing important features.

3. Step 3: Compare options

   Embedding -> Bidirectional(LSTM with return_sequences=True) -> GlobalMaxPooling1D -> Dense uses Bidirectional LSTM with return_sequences=True plus pooling, best for full context and fixed vector. Embedding -> Bidirectional(LSTM with return_sequences=False) -> Dense skips pooling, output is last timestep only. Embedding -> LSTM with return_sequences=False -> Dense is unidirectional. Embedding -> Bidirectional(LSTM with return_sequences=True) -> Dense outputs sequence but no pooling, so Dense gets sequence input, causing shape issues.

4. Final Answer:

   Embedding -> Bidirectional(LSTM with return_sequences=True) -> GlobalMaxPooling1D -> Dense -> Option A

5. Quick Check:

   Pooling after bidirectional LSTM = A [OK]

Hint: Use pooling after return_sequences=True for fixed vector [OK]

Common Mistakes:

• Using return_sequences=False loses sequence info
• Skipping pooling leads to shape mismatch
• Using unidirectional LSTM loses backward context