Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Save more on your purchases now! discount-offer-chevron-icon
Savings automatically calculated. No voucher code required.
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Natural Language Processing Fundamentals

You're reading from   Natural Language Processing Fundamentals Build intelligent applications that can interpret the human language to deliver impactful results

Arrow left icon
Product type Paperback
Published in Mar 2019
Publisher
ISBN-13 9781789954043
Length 374 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (2):
Arrow left icon
Dwight Gunning Dwight Gunning
Author Profile Icon Dwight Gunning
Dwight Gunning
Sohom Ghosh Sohom Ghosh
Author Profile Icon Sohom Ghosh
Sohom Ghosh
Arrow right icon
View More author details
Toc

Table of Contents (10) Chapters Close

Preface 1. Introduction to Natural Language Processing FREE CHAPTER 2. Basic Feature Extraction Methods 3. Developing a Text classifier 4. Collecting Text Data from the Web 5. Topic Modeling 6. Text Summarization and Text Generation 7. Vector Representation 8. Sentiment Analysis Appendix

Generating Text with Markov Chains

One of the more interesting uses of NLP is generating text, whether for amusement, for research, or for profit. The key concept in generating text is to take advantage of the statistical properties of the text. This makes the output text more realistic and, more importantly, we gain information about the text itself if we can rearrange it to identify interesting patterns in it. Text can be generated in many different ways. We will explore doing so using Markov chains.

Markov Chains

A Markov chain is a mathematical system for transitioning between states based on probabilities. No matter how a system arrives at its present state, the possible future states are all predetermined. Furthermore, the move to the next state is based on a set of probabilities. Markov chains operate in timesteps. After each timestep, the system selects a new state. This new state is chosen based on the current state and the probabilities of the future states.

Markov...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime