Book Image

Deep Learning for Natural Language Processing

By : Karthiek Reddy Bokka, Shubhangi Hora, Tanuj Jain, Monicah Wambugu
Book Image

Deep Learning for Natural Language Processing

By: Karthiek Reddy Bokka, Shubhangi Hora, Tanuj Jain, Monicah Wambugu

Overview of this book

Applying deep learning approaches to various NLP tasks can take your computational algorithms to a completely new level in terms of speed and accuracy. Deep Learning for Natural Language Processing starts by highlighting the basic building blocks of the natural language processing domain. The book goes on to introduce the problems that you can solve using state-of-the-art neural network models. After this, delving into the various neural network architectures and their specific areas of application will help you to understand how to select the best model to suit your needs. As you advance through this deep learning book, you’ll study convolutional, recurrent, and recursive neural networks, in addition to covering long short-term memory networks (LSTM). Understanding these networks will help you to implement their models using Keras. In later chapters, you will be able to develop a trigger word detection application using NLP techniques such as attention model and beam search. By the end of this book, you will not only have sound knowledge of natural language processing, but also be able to select the best text preprocessing and neural network models to solve a number of NLP issues.

Related Content you might be interested in

Current Title:

Small book image
Deep Learning for Natural Language Processing
Karthiek Reddy Bokka | Shubhangi Hora | Tanuj Jain | Monicah Wambugu
Jun, 2019 | 372 pages
Small book image
Hands-On Python Natural Language Processing
Mayank Rasu | Aman Kedia
Jun, 2020 | 316 pages
Small book image
Intelligent Projects Using Python
Santanu Pattanayak
Jan, 2019 | 342 pages
Small book image
Hands-On Natural Language Processing with Python
Chaitanya Joshi | Auguste Byiringiro | Rajesh Arumugam | Rajalingappaa Shanmugamani | Karthik Muthuswamy
Jul, 2018 | 312 pages
Table of Contents (11 chapters)
About the Book
About the Book
About the Authors
Description
Learning Objectives
Audience
Approach
Hardware Requirements
Software Requirements
Conventions
Installation and Setup
Install Python on Windows
Install Python on Linux
Install Python on macOS X
Installing Keras
Additional Resources
Free Chapter
1
Introduction to Natural Language Processing
Introduction to Natural Language Processing
Introduction
The Basics of Natural Language Processing
Capabilities of Natural language processing
Applications of Natural Language Processing
Word Embeddings
Summary
2
Applications of Natural Language Processing
Applications of Natural Language Processing
Introduction
POS Tagging
Applications of Parts of Speech Tagging
Chunking
Chinking
Named Entity Recognition
Summary
3
Introduction to Neural Networks
Introduction to Neural Networks
Introduction
Neural Networks
Training a Neural Network
Designing a Neural Network and Its Applications
Fundamentals of Deploying a Model as a Service
Summary
4
Foundations of Convolutional Neural Network
Foundations of Convolutional Neural Network
Introduction
Understanding the Architecture of a CNN
Training a CNN
Application Areas of CNNs
Summary
5
Recurrent Neural Networks
Recurrent Neural Networks
Introduction
Previous Versions of Neural Networks
RNNs
Updates and Gradient Flow
Gradients
Summary
6
Gated Recurrent Units (GRUs)
Gated Recurrent Units (GRUs)
Introduction
The Drawback of Simple RNNs
Gated Recurrent Units (GRUs)
Sentiment Analysis with GRU
Summary
7
Long Short-Term Memory (LSTM)
Long Short-Term Memory (LSTM)
Introduction
The Input Gate and the Candidate Cell State
Output Gate and Current Activation
Neural Language Translation
Summary
8
State-of-the-Art Natural Language Processing
State-of-the-Art Natural Language Processing
Introduction
Other Architectures and Developments
Activity 11: Build a Text Summarization Model
Summary
9
A Practical NLP Project Workflow in an Organization
A Practical NLP Project Workflow in an Organization
Introduction
Problem Definition
Data Acquisition
Google Colab
Flask
Deployment
Summary
Appendix
Appendix
Chapter 1: Introduction to Natural Language Processing
Chapter 2: Applications of Natural Language Processing
Chapter 3: Introduction to Neural Networks
Chapter 4: Introduction to convolutional networks
Chapter 5: Foundations of Recurrent Neural Network
Chapter 6: Foundations of GRUs
Chapter 7: Foundations of LSTM
Chapter 8: State of the art in Natural Language Processing
Chapter 9: A practical NLP project workflow in an organisation

Training a CNN

During the training of a CNN, the model tries to learn the weights of the filters in feature extraction and the weights at the fully connected layers in the neural network. To understand how a model is trained, we'll discuss how the probability of each output class is calculated, how we calculate the error or the loss, and finally, how we optimize or minimize that loss while updating the weights:

  1. Probabilities

    Recall that in the last layer of the neural network section, we used a softmax function to calculate the probability of each output class. This probability is calculated by dividing the exponent of that class score by the sum of the exponents of all scores:

    Figure 4.12: Expression to calculate probability
    Figure 4.12: Expression to calculate probability
  2. Loss

    We need to be able to quantify how well the calculated probabilities predict the actual class. This is done by calculating a loss, which in the case of classification probability is best done through the categorical cross-entropy loss function. The categorical...

Previous Section
End of Section 4
Next Section