Say I have a sentence like 'I refuse to fly' or 'I'd like to fly'. I also have a sentence like 'I don't want to sit'. When training custom intents in one of the available NLU engines (rasa/wit/luis), what's the best way to go for modeling: Naively I could have: RefuseFlyIntent,WantFlyIntent,and RefuseSit and WantSit
More sophisticated, have set of intents FlyIntent, SitIntent, WantIntent, RefuseIntent, and have my code process the combinations.
same question can apply for other cases, like how to model the difference between You Like To Fly and I Like To Fly
I'm sure there are known methodologies for that, wanted to understand what they are. If you could give me links to literature about it, would be great.
many thanks, Lior
This is a common mistake people do when designing conversations.
Intents
point to a specific action. In your example, the action is whether or not tofly.
To get a better understanding, If more than one statement looks alike with only a few words differing make it entities of a single intent.