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.
Table of Contents (11 chapters)

Introduction

Neural networks, as a broad field, borrow a lot from biological systems, particularly the brain. Advances in neural science have directly influenced research in to neural networks.

CNNs are inspired by the work of two neural scientists, D.H. Hubel and T.N. Wiesel. Their research focused on the mammalian visual cortex, which is the part of the brain responsible for vision. Through their research back in the sixties, they found that the visual cortex is composed of layers of neurons. Furthermore, these layers are arranged in a hierarchical structure. This hierarchy ranges from simple-to hypercomplex neurons. They also advanced the notion of a 'receptive field,' which is the space within which certain stimuli activate or fire a neuron, with a degree of spatial invariance. Spatial or shift invariance allows animals to detect objects regardless of whether they are rotated, scaled, transformed, or partially obscured.

Figure 4.1: Examples of spatial variance

Inspired...