IBM Watson™ Natural Language Understanding Service Ideas

Welcome to the IBM Watson™ Natural Language Understanding Service Ideas Portal


We welcome and appreciate your feedback on the IBM Watson™ Natural Language Understanding Service to help make it even better than it is today!


The ideas portal is for sharing ideas and feature requests with us that will make the IBM Watson™ Natural Language Understanding Service better. If you are looking for troubleshooting help or wondering how to use the service, please check the IBM Watson™ Natural Language Understanding Service 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.

Add default entities like location and amount

The Watson conversation service has the ability to identify both numeric digits and numeric text. I would like the NLU service to have these default entities supported so that I can train models in Knowledge studio with both text and digits. Currently, I am running a file through speech to text which returns numeric text (e.g. eight hundred). The NLU models are trained on digits (e.g. 800) I have to run the text through conversation then into NLU in order for the models to return correctly.

  • George Foster
  • Sep 6 2017
  • Planned
  • Attach files
  • Michel van Der Poorten commented
    September 13, 2017 05:12

    George, I know that the system entities in Conversation are being redeveloped. It might be interesting to have them as a separate API (or micro-service) so it can be used all kinds of APIs such as NLU but also WKS...

  • Admin
    STEFAN TZANEV commented
    September 14, 2017 13:32

    George,

    Thanks for taking time to post your idea. This NLU enhancement is already on the NLU roadmap here: https://bigblue.aha.io/features/NLU-158

    (As an IBMer you should already have "viewer" access to Aha!. If you have issues with your Aha! access, instructions for access are available here: https://bigblueaha.w3ibm.mybluemix.net/)