Natural Language Processing with TensorFlow: Teach language to machines using Python's deep learning library

Ganegedara, Thushan

ISBN 10: 1788478312 / ISBN 13: 9781788478311

Published by Packt Publishing, 2018

About this Item

Most items will be dispatched the same or the next working day. A copy that has been read but remains in clean condition. All of the pages are intact and the cover is intact and the spine may show signs of wear. The book may have minor markings which are not specifically mentioned. Previously water damaged, slight waving to the pages.

Seller Inventory # wbb0021520263

Bibliographic Details

• Title: Natural Language Processing with TensorFlow: Teach language to machines using Python's deep learning library
• Publisher: Packt Publishing
• Publication Date: 2018
• Language: English
• ISBN 10: 1788478312
• ISBN 13: 9781788478311
• Binding: Soft cover
• Condition: Good
• Weight: 820 grams

About this title

Synopsis

Key Features

• Focus on natural language processing with TensorFlow, thereby avoiding the traditional focus on computer vision
• Treats NLP as a field in its own right, and learn to process and evaluate large unstructured data sets consisting of text
• Learn to apply the TensorFlow toolbox to the most interesting field in artificial intelligence

Book Description

TensorFlow is the most important deep learning framework currently in existence. Deep Learning algorithms are the most important frontier in artificial intelligence, with natural language processing (NLP) providing much of the engineering required to understand and process the vast majority of data available to deep learning applications today. Natural Language Processing with TensorFlow teaches aspiring deep learning developers to cope with unstructured data, that is, text and audio, which make up a large part of currently available data streams.

Thushan Ganegedara starts out by explaining the inner workings of TensorFlow itself, and the proceeds with a family of algorithms allowing sequences of words to be turned into vectors, making them accessible to deep learning algorithms in the process. He then shifts gears somewhat by showing how classical deep learning algorithms like convolutional neural networks (CNN) and recurrent neural (RNN) networks can be applied to NLP. Long short-term memory are a variety of RNNs, used in the next chapter for text generation.

Thushan concludes the book with an overview and implementation of neural machine translation, a method relying on deep learning algorithms to achieve impressive results in machine translation.

What you will learn

• How to master NLP based on existing TensorFlow algorithms
• Build NLP applications
• Write automatic translation programs using neural machine translation algorithms
• Use classical deep learning algorithms to classify sentences
• Apply Long Short-Term Memory to text generation

About the Author

Thushan is a seasoned ML practitioner with 4+ years of experience in the industry. Currently he is a senior machine learning engineer at Canva; an Australian startup that founded the online visual design software, Canva, serving millions of customers. His efforts are particularly concentrated in the search and recommendations group working on both visual and textual content. Prior to Canva, Thushan was a senior data scientist at QBE Insurance; an Australian Insurance company. Thushan was developing ML solutions for use-cases related to insurance claims. He also led efforts in developing a Speech2Text pipeline there. He obtained his PhD specializing in machine learning from the University of Sydney in 2018.