Skip to content

fix small grammatical error in Use a None intent #189

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 26, 2018
Merged

fix small grammatical error in Use a None intent #189

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion articles/v4sdk/bot-builder-concept-luis.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ LUIS apps recognize intent by classifying an utterance into one of multiple cate
One way of reducing the number of intents is to use a hierarchical design. Consider the case of a personal assistant bot that has three intents related to weather, three intents related to home automation, and three other utility intents which are Help, Cancel and Greeting. If you put all the intents in the same LUIS app, you already have 9, and as you add features to the bot, you could end up with dozens. Instead, you can use a dispatcher LUIS app to determine whether the user's request is for weather, home automation, or utility, then call the LUIS app for the category that the dispatcher determines. In this case each of the LUIS apps only starts with 3 intents.

### Use a None intent
It's often the case that users of your bot will say something unexpected or unrelated to the current conversation flow. The None intent is provided for handling those messages. If you don't train an intent for handling the fallback, default or "none of the above" cases, your LUIS app can only classify messages into the into intents it has defined. So for example, let's say you have a LUIS app with two intents: `HomeAutomation.TurnOn` and `HomeAutomation.TurnOff`. If those are the only intents, and the input is something unrelated like "schedule an appointment on Friday", your LUIS app has no choice but to classify that message as either HomeAutomation.TurnOn or HomeAutomation.TurnOff. If your LUIS app has a `None` intent with a few examples, you can provide some fallback logic in your bot to handle unexpected utterances.
It's often the case that users of your bot will say something unexpected or unrelated to the current conversation flow. The None intent is provided for handling those messages. If you don't train an intent for handling the fallback, default or "none of the above" cases, your LUIS app can only classify messages into the intents it has defined. So for example, let's say you have a LUIS app with two intents: `HomeAutomation.TurnOn` and `HomeAutomation.TurnOff`. If those are the only intents, and the input is something unrelated like "schedule an appointment on Friday", your LUIS app has no choice but to classify that message as either HomeAutomation.TurnOn or HomeAutomation.TurnOff. If your LUIS app has a `None` intent with a few examples, you can provide some fallback logic in your bot to handle unexpected utterances.

### Review the utterances that LUIS app receives
LUIS apps provide a feature for improving your app performance, by reviewing messages that users sent to it. See [Review suggested utterances](https://docs.microsoft.com/en-us/azure/cognitive-services/LUIS/label-suggested-utterances) for a step-by-step walkthrough.
Expand Down