Skip to Main Content
IBM Data and AI Ideas Portal for Customers

Shape the future of IBM!

We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:

Post your ideas

Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,

  1. Post an idea

  2. Upvote ideas that matter most to you

  3. Get feedback from the IBM team to refine your idea

Help IBM prioritize your ideas and requests

The IBM team may need your help to refine the ideas so they may ask for more information or feedback. The product management team will then decide if they can begin working on your idea. If they can start during the next development cycle, they will put the idea on the priority list. Each team at IBM works on a different schedule, where some ideas can be implemented right away, others may be placed on a different schedule.

Receive notification on the decision

Some ideas can be implemented at IBM, while others may not fit within the development plans for the product. In either case, the team will let you know as soon as possible. In some cases, we may be able to find alternatives for ideas which cannot be implemented in a reasonable time.

Additional Information

To view our roadmaps:

Reminder: This is not the place to submit defects or support needs, please use normal support channel for these cases

IBM Employees:

The correct URL for entering your ideas is:



Natural Language Understanding (NLU)

Showing 28

Relation argument offsets relative to the html

The relation argument offsets come back relative to the Discovery text, but if you want to do something useful with those offsets it would probably be to add tags to the html. Computing the corresponding offset in the html is possible, but inconve...
about 4 years ago in Natural Language Understanding (NLU) 0 Future consideration

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...
over 4 years ago in Natural Language Understanding (NLU) 0 Future consideration

Developing new languages for Central Europe (Czech, Bulgarian, Slovakian, Magyar)

Hi, a major bank, KBC, is working across Europe and wants to deploy one AI technology across the group. They've started off with Watson Conversation service in Dutch and are very happy with the quality. Considering WDS is coming now in Dutch, th...
over 4 years ago in Natural Language Understanding (NLU) 1 Future consideration

Ability to use multiple WKS custom models during enrichment

Many a time the number of entity & relation types can grow to the order of a few hundred's and hence will need to be built & maintained across multiple WKS projects. This would mean during enrichment I would need the ability to specify the...
over 4 years ago in Natural Language Understanding (NLU) 1 Planned for future release

Create a rest endpoint to duplicate WKS custom model instance.

Currently, we are unable to scale to more than 20 threads when using a WKS custom model for entity and relation prediction with the NLU service. Our documents are very large and one document can take up to 5 minutes to process. If we have multiple...
over 4 years ago in Natural Language Understanding (NLU) 0 Future consideration

Deploy models programmatically

I'd like to automate the process of building, training, and deploying NLU models. This is a larger feature track of work.
almost 5 years ago in Natural Language Understanding (NLU) 1 Future consideration

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. Curre...
almost 5 years ago in Natural Language Understanding (NLU) 2 Planned for future release

Remove session cookie from NLU calls

When I use postman I am returned a cookie that allows me to make unauthenticated calls into the NLU system. This leads to a vulnerable API due to session hijacking. [1] To test this I made a call to get a list of models, removed my auth head, and ...
almost 5 years ago in Natural Language Understanding (NLU) 1 Future consideration