IBM Watson™ Ideas

Welcome to the IBM Watson™ Ideas Portal

We welcome and appreciate your feedback on IBM Watson™ Products to help make them even better than they are today!

If you are looking for troubleshooting help or wondering how to use our products and services, please check the IBM Watson™ documentation. Please do not use the Ideas Portal for reporting bugs - we ask that you report bugs or issues with the product by contacting IBM support.

Before you submit an idea, please perform a search first as a similar idea may have already been reported in the portal.

If a related idea is not yet listed, please create a new idea and include with it a description which includes expected behavior as well as why having this feature would improve the service and how it would address your use case.

Back-off to general models when using grammars

In our use of STT for Conversation Watson Assistant, we had many cases (responses expecting codes etc) where the grammar functionality would be extremely useful useful but for natural deployment a "fall back" to general  recognition models would be needed. The particular form of the codes we were looking at for this customer was things like "R01" or "R23", which are problematic for reasons that should be obvious.  This would allow us to support both interactions of the form:

Watson: "Okay, what is your error code?"
User: "R23"

As well as:

Watson: "Okay, what is your error code?"
User: "I'm sorry, can you tell me where to find that?"

  • Guest
  • Mar 22 2018
  • Needs review
Why is it useful?
Who would benefit from this IDEA? As a STT customizer, I could provide my Watson Assistant colleague with a customization of the STT service that is effective recognizing short structured inputs as well as general inputs
How should it work?
Idea Priority
Priority Justification
Customer Name
Submitting Organization
Submitter Tags
  • Attach files