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.
Why is it useful?
|Who would benefit from this IDEA?||As a user I want NLU to have default system entities like the conversation service|
How should it work?