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.

Verbose output of all WKS model features

Please enable the access to all the features that will be annotated by a WKS model - similar to the "verbose" functionality in the deprecated Alchemy API. We need to have access to the confidence score of annotated Entities, to annotated roles and all the other information, a WKS model has been trained on.

  • Christina Niegel
  • Mar 12 2018
  • Future Consideration
Why is it useful?
Who would benefit from this IDEA? Since WKS is a statistical model, we always need to consider the confidence of an annotation. Every NLP project will benefit from this information.
How should it work?
Idea Priority
Priority Justification
Customer Name
Submitting Organization
Submitter Tags
  • Attach files
  • Franny Hsiao commented
    25 Jun, 2018 12:58pm

    in addition to confidence scores, POS info not accessible, one major change is that the coref chains are no longer visible after training. this makes debugging very difficult when anaphora are resolved incorrectly. Please make these available in the output as well