Packt+ | Advance your knowledge in tech

You're reading from Hands-On Natural Language Processing with Python A practical guide to applying deep learning architectures to your NLP applications

Product type Paperback

Published in Jul 2018

Publisher Packt

ISBN-13 9781789139495

Length 312 pages

Edition 1st Edition

Languages

Processing

Tools

NLTK

Concepts

Deep Learning

Authors (2):

Rajalingappaa Shanmugamani

Rajesh Arumugam

View More author details

Table of Contents (20) Chapters

Title Page

Packt Upsell

Foreword

Contributors

Preface

1. Getting Started

2. Text Classification and POS Tagging Using NLTK FREE CHAPTER

3. Deep Learning and TensorFlow

4. Semantic Embedding Using Shallow Models

5. Text Classification Using LSTM

6. Searching and DeDuplicating Using CNNs

7. Named Entity Recognition Using Character LSTM

8. Text Generation and Summarization Using GRUs

9. Question-Answering and Chatbots Using Memory Networks

10. Machine Translation Using the Attention-Based Model

11. Speech Recognition Using DeepSpeech

12. Text-to-Speech Using Tacotron

13. Deploying Trained Models

1. Other Books You May Enjoy

Leave a review - let other readers know what you think

Index

TensorFlow

TensorFlow is a library provided by Google for ML. It is fast and scalable. TensorFlow has a wide variety of tools for visualization and deployment. It has gained popularity in the developer community and has been used in several organizations. In this section, you will see hardware requirements, installation, and a couple of simple examples.

General Purpose – Graphics Processing Unit

A General Processing – Graphics Processing Unit (GPGPU) can accelerate deep learningmodel training and inference to a great extent. Recent advances in deep learning have been possible because of big data and cheap computation. The company, Nvidia, provides GPUs and some libraries to accelerate deep learning. Having GPU hardware for training is useful, but not necessary.

CUDA

The Compute Unified Device Architecture (CUDA) library provided by Nvidia will install the required drivers for the GPU. Go to https://developer.nvidia.com/cuda-downloads and access the following screen: