如何在使用LUIS/WIT Intent时消除负面言论 [英] How to eliminate negative utterances while using LUIS/WIT Intent
问题描述
我有一个意图"BookTicket" . 我几乎没有话要说:预订车票",预订我的车票" .....很好.
I have an intent "BookTicket". I have few utterances for the same: "book a ticket", "book my ticket".....it works fine.
它也可以与不预订门票",预订我的表演" 一起使用.我的问题是:如何消除这些否定搜索来搜索上述意图并返回错误消息,而不是调用意图.
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.
现在,我正在使用LUIS框架进行尝试.
Right now, I am trying this with LUIS framework.
谢谢
推荐答案
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.
这篇关于如何在使用LUIS/WIT Intent时消除负面言论的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!