Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
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
Cognitive Computing with IBM Watson

You're reading from   Cognitive Computing with IBM Watson Build smart applications using artificial intelligence as a service

Arrow left icon
Product type Paperback
Published in Apr 2019
Publisher Packt
ISBN-13 9781788478298
Length 256 pages
Edition 1st Edition
Arrow right icon
Authors (2):
Arrow left icon
Tanmay Bakshi Tanmay Bakshi
Author Profile Icon Tanmay Bakshi
Tanmay Bakshi
Robert High Robert High
Author Profile Icon Robert High
Robert High
Arrow right icon
View More author details
Toc

Table of Contents (11) Chapters Close

Preface 1. Background, Transition, and the Future of Computing FREE CHAPTER 2. Can Machines Converse Like Humans? 3. Computer Vision 4. This Is How Computers Speak 5. Expecting Empathy from Dumb Computers 6. Language - How Watson Deals with NL 7. Structuring Unstructured Content Through Watson 8. Putting It All Together with Watson 9. Future - Cognitive Computing and You 10. Another Book You May Enjoy

Using a custom model in NLU


Once you have deployed a model to your NLU instance, you can reference that model in the feature attributes for either entities or relations (or both).

The following are the steps:

  1. You need the Model ID, which you can get through the List models method on the NLU service, or more easily from the Model ID listed in the Version History and Deployment tab of Knowledge Studio:
  1. Reference that model ID in your call to the analyze method:
entities=EntitiesOptions(limit=100, mentions=True, sentiment=True, emotion=True, model='7a8d0323-939b-4dbc-afa8-1a60d7966c67')
  1. When you run the analyze method again with this model, you should see dramatically different results than the entity analysis. It might look something like this:
The following entities were found:
[British] of type <ORGANIZATION> was found 1 times, with 0% confidence.
The entity was found in:
"British", at index 55
The emotional scores for this entity are: 12% Anger; 2% Disgust; 15% Fear; 63% Joy; and 3% Sadness...
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
Banner background image