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)

Problem Definition

Let's say that you work for an e-commerce platform, through which your customers can purchase a variety of products. The merchandising department of your company comes up with a request to add a feature to the website – 'Addition of a slider that contains the 5 items that received the most positive reviews in a given calendar week'.

This request is first made to the web development department since, ultimately, they are the ones responsible for displaying the website contents. The web development department realizes that, to get a review rating, the data science team needs to be involved. The data science team receives the request from the web development team – 'We need a web service that takes a string of text as input and returns a score that indicates the degree to which the text represents a positive sentiment'.

The data science team then refines the requirements and agrees upon the definition of a Minimum Viable Product (MVP)...