LSTM for text in NLP

Introduction

LSTM helps computers understand and remember words in sentences. It is good for tasks like predicting the next word or classifying text.

When you want to predict the next word in a sentence, like in text messaging apps.

When you want to classify emails as spam or not spam.

When you want to analyze the sentiment of a review (happy or sad).

When you want to generate text, like writing a story or poem.

When you want to understand the meaning of a sentence over time.

Syntax

NLP

model = Sequential()
model.add(Embedding(input_dim=vocab_size, output_dim=embedding_dim, input_length=max_length))
model.add(LSTM(units=hidden_units))
model.add(Dense(units=num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

Embedding layer turns words into numbers that the model can understand.

LSTM layer remembers important information from the text.

Examples

This example builds an LSTM model for text classification with 5 classes.

NLP

model = Sequential()
model.add(Embedding(10000, 64, input_length=100))
model.add(LSTM(128))
model.add(Dense(5, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

This example uses two LSTM layers for binary sentiment analysis.

NLP

model = Sequential()
model.add(Embedding(5000, 32, input_length=50))
model.add(LSTM(64, return_sequences=True))
model.add(LSTM(32))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Sample Model

This program trains a small LSTM model to classify short sentences as positive or negative. It shows training accuracy and predicted classes.

NLP

import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, LSTM, Dense
from tensorflow.keras.utils import to_categorical

# Sample text data: sentences and labels
texts = ['I love machine learning', 'This is a great movie', 'I hate bad weather', 'This movie is terrible']
labels = [1, 1, 0, 0]  # 1=positive, 0=negative

# Simple word index
word_index = {'i':1, 'love':2, 'machine':3, 'learning':4, 'this':5, 'is':6, 'a':7, 'great':8, 'movie':9, 'hate':10, 'bad':11, 'weather':12, 'terrible':13}

# Convert texts to sequences of integers
max_length = 5
sequences = []
for text in texts:
    seq = [word_index[word.lower()] for word in text.split()]
    # Pad sequences with zeros if shorter than max_length
    seq += [0] * (max_length - len(seq))
    sequences.append(seq)

X = np.array(sequences)
y = to_categorical(labels, num_classes=2)

# Build LSTM model
model = Sequential()
model.add(Embedding(input_dim=14, output_dim=8, input_length=max_length))
model.add(LSTM(16))
model.add(Dense(2, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# Train model
history = model.fit(X, y, epochs=10, verbose=0)

# Predict on training data
predictions = model.predict(X)
predicted_classes = np.argmax(predictions, axis=1)

print(f'Training accuracy: {history.history["accuracy"][-1]:.2f}')
print('Predicted classes:', predicted_classes.tolist())

Important Notes

LSTM is good at remembering the order of words, which is important in sentences.

Embedding size and LSTM units can be changed to improve model performance.

For real projects, use more data and proper text preprocessing.

Summary

LSTM models help understand text by remembering word order.

They are useful for tasks like sentiment analysis and text classification.

Embedding layers convert words into numbers before LSTM processes them.

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