Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Conversational AI with Rasa

You're reading from  Conversational AI with Rasa

Product type Book
Published in Oct 2021
Publisher Packt
ISBN-13 9781801077057
Pages 264 pages
Edition 1st Edition
Languages
Authors (2):
Xiaoquan Kong Xiaoquan Kong
Profile icon Xiaoquan Kong
Guan Wang Guan Wang
Profile icon Guan Wang
View More author details

Table of Contents (16) Chapters

Preface Section 1: The Rasa Framework
Chapter 1: Introduction to Chatbots and the Rasa Framework Chapter 2: Natural Language Understanding in Rasa Chapter 3: Rasa Core Section 2: Rasa in Action
Chapter 4: Handling Business Logic Chapter 5: Working with Response Selector to Handle Chitchat and FAQs Chapter 6: Knowledge Base Actions to Handle Question Answering Chapter 7: Entity Roles and Groups for Complex Named Entity Recognition Chapter 8: Working Principles and Customization of Rasa Section 3: Best Practices
Chapter 9: Testing and Production Deployment Chapter 10: Conversation-Driven Development and Interactive Learning Chapter 11: Debugging, Optimization, and Community Ecosystem Other Books You May Enjoy

Using entity groups to divide entities into groups

Sometimes, there will be multiple groups of entities, where each group belongs to one subtask. Entities need to be grouped into subtasks based on semantics. Let's take a look at an example of ordering drinks. A customer could order two drinks, where one is a large cup of juice with ice and the other one is a medium cup of soda without ice. User expressions can be versatile, and if entities are not grouped, the bot system won't be able to understand the configurations of the two separate drinks.

Rasa offers the use of entity groups to tackle this challenge. With entity groups, an entity not only has entity type, but it also has group information, which indicates the subtask that it belongs to.

To use entity groups, we need to annotate our training data with the group information along with the entity type. Some sample training data appears as follows:

Hi, I'd like to order two drinks. One [large cup]{"entity...
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 $15.99/month. Cancel anytime}