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,
Post an idea
Upvote ideas that matter most to you
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.
Often a single concept is repeated in many different intents. If that concept were defined as an entity and that entity includable as part of an example of an intent, it would greatly simplify the definitions of intents.
For example, suppose the chatbot concerns EU GDPR. There will be many intents around the concept of personal data, such as:
Do you collect personal data?
How do you use personal data?
How can I change my personal data?
However, "personal data" might be written as "personal data", "personal information", "personal info", "my data", "pd", and many others, including misspellings and other variants. All of these variants should be included in examples of intents, making the creation of intents very tedious and error prone.
Thus, if "personal-data" were defined as in entity and then included within examples of intents:
Defining of intents could be vastly simplified
It could be much easier to train Watson to recognize all the intents using a given entity, rather than having to train each intent separately
You could avoid forgetting to include certain examples within intents
Do not place IBM confidential, company confidential, or personal information into any field.