How to eliminate negative utterances while using LUIS/WIT Intent

Question

I have an intent "BookTicket". I have few utterances for the same: "book a ticket", "book my ticket".....it works fine.

It also works with "do not book a ticket", "book my show". My question is: How can I eliminate these negative searches to search for the intent mentioned above and return an error message instead of invoking the intent.

Right now, I am trying this with LUIS framework.

thanks

Harrelson

Answer 1

In case of LUIS, use the None intent to mark the negative examples you want to eliminate, this way your model will learn to associate these negative utterances with None intent not "BookTicket"

Margie

Thanks. Is there any in-built functionality to identity these negative utterances. – Harrelson

URW. There's no builtin functionality at the current time, but you can use the suggest tab (if the API is already released) to detect these negative utterances and mark them with the None intent. – Margie

Answer 2

My be you can try this https://azure.microsoft.com/en-in/documentation/articles/machine-learning-apps-text-analytics/ . Set the threshold as required to your project so that only positive will come out.

Marta

Answer 3

Google brought me here so I'm posting this for anyone who finds it useful.

Microsoft documentation states: "you can create two intents (one positive, and one negative) and add appropriate utterances for each. Or you can create a single intent and mark the two different positive and negative terms as an entity."

Prologue