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

Text summarization

Text summarization is the process of transforming an input document into a short summary, to help us understand the main content of the document in a short amount of time. Fundamentally, there are two types of summarization. One of them is extractive summarization and the other is abstractive summarization. We will briefly look at descriptions of these types of summaries.

Extractive summarization

In this type of summarization, the important phrases or keywords in a document are extracted and concatenated to get a short summary.

The main advantage is that it is simple and robust, since the extracted text is taken directly from the document. The disadvantage of this method is that we may not be able to obtain new paraphrasing, which produces clarity in the summary. In the next section, we will briefly look at extractive summarization using gensim.