Preprocessing - Stemming and Lemmatization
LUIS gives different scores for "book ticket" and "book tickets". Rather than adding all possible utternace variations, if options stemming and lemmatization can be supported then it can reduce the training burdon.
Or if LUIS is handling this kind of situation internally then please suggest
This is currently on our roadmap.
There is an unanswered similar question : https://stackoverflow.com/questions/45096432/is-any-text-pre-processing-recommended-for-luis-bot-app