LSTM for text in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does LSTM stand for in machine learning?

LSTM stands for Long Short-Term Memory. It is a type of neural network designed to remember information for long periods, especially useful for sequences like text.

intermediate

Why are LSTMs better than simple RNNs for text data?

LSTMs can remember important information over longer sequences and avoid the problem of forgetting early data, which simple RNNs struggle with due to vanishing gradients.

intermediate

Name the three main gates inside an LSTM cell.

The three main gates are: Forget Gate (decides what to forget), Input Gate (decides what new information to add), and Output Gate (decides what to output).

beginner

How does an LSTM process a sentence for text classification?

An LSTM reads the sentence word by word, updating its memory at each step. After the last word, it uses the final hidden state to predict the sentence's category.

beginner

What is a common metric to evaluate LSTM models on text classification tasks?

Accuracy is commonly used to measure how many sentences the LSTM correctly classifies out of all tested sentences.

What problem does an LSTM solve better than a simple RNN?

A Remembering long-term dependencies in sequences

B Faster training on images

C Reducing model size

D Handling missing data

LSTMs are designed to remember information over long sequences, which simple RNNs struggle with.

Which gate in an LSTM decides what information to forget?

A Input Gate

B Forget Gate

C Output Gate

D Memory Gate

The Forget Gate controls which information is removed from the cell's memory.

In text classification, what does the LSTM use to make the final prediction?

A The final hidden state after reading the sentence

B The average of all word embeddings

C The first word embedding

D The length of the sentence

The final hidden state summarizes the entire sentence and is used for prediction.

Which of these is NOT a typical use of LSTMs?

A Text generation

B Speech recognition

C Machine translation

D Image classification

Image classification usually uses convolutional neural networks, not LSTMs.

What is a common input format for LSTM models working on text?

A Raw text strings

B Pixel values

C One-hot encoded vectors or word embeddings

D Audio waveforms

LSTMs require numerical input like one-hot vectors or embeddings representing words.

Explain how an LSTM processes a sentence step-by-step for text classification.

Think about how the LSTM reads and remembers words in order.

Describe the role of the forget, input, and output gates inside an LSTM cell.

Each gate controls a different part of the memory update.

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