I am trying to figure out how the CLU model classifies an utterance to an intent and how is the score, mentioned next to the intent, calculated?
If I put in a query like "Today is such a good day" and I want the intent to be "Happy", considering I have given 10 example utterances under intent "Happy", is each phrase in the query like "Today", "is", "such", "a", "good", "day" mapped to each example utterance to find a match of similar phrases based on which score is given or is it classifying in some other way?
I was looking for an answer here: [https://learn.microsoft.com/en-us/azure/cognitive-services/language-service/conversational-language-understanding/overview](CLU Documentation).
I could not find how the score for each intent is calculated and how classification is working. Please let me know if I am missing something.