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

score 1 · Answer 1 · answered Jul 21 '16 at 14:35

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"

answered Jul 21 '16 at 14:35

Mokhtar Ashour

600
2
9
21

Thanks. Is there any in-built functionality to identity these negative utterances. – Satyajit Jul 22 '16 at 07:43
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. – Mokhtar Ashour Jul 22 '16 at 13:31

score 1 · Answer 2 · answered Jul 24 '16 at 18:53

1

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.

answered Jul 24 '16 at 18:53

KBKR

11
1

score 0 · Answer 3 · answered Feb 17 '21 at 09:29

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."

How to eliminate negative utterances while using LUIS/WIT Intent

3 Answers3

Linked