Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
This article provides quick answers to essential FAQs about conversational language understanding.
How do I create a project?
Use the quickstart to get started creating your first project, or the how-to article for more details.
Can I use more than one conversational language understanding project together?
Yes, using orchestration workflow. For more information, see the orchestration workflow documentation.
What is the difference between language understanding and conversational language understanding?
Conversational language understanding is the next generation of LUIS.
Training is taking a long time, is this behavior expected?
For conversation projects, long training times are expected. Based on the number of examples you have your training times may vary from 5 minutes to 1 hour or more.
How do I use entity components?
See the entity components article.
Which languages are supported in this feature?
See the language support article.
How do I get more accurate results for my project?
Take a look at the recommended guidelines for information on improving accuracy.
How do I get predictions in different languages?
When you train and deploy a conversation project in any language, you can immediately try querying it in multiple languages. You may get varied results for different languages. To improve the accuracy of any language, add utterances to your project in that language to introduce the trained model to more syntax of that language.
How many intents, entities, utterances can I add to a project?
See the service limits article.
Can I label the same word as two different entities?
Unlike LUIS, you can't label the same text as two different entities. Learned components across different entities are mutually exclusive, and only one learned span is predicted for each set of characters.
Can I import a LUIS JSON file into conversational language understanding?
Yes, you can import any LUIS application JSON file from the latest version in the service.
Can I import a LUIS .LU file into conversational language understanding?
No, the service only supports JSON format. You can go to LUIS, import the .LU file, and export it as a JSON file.
Can I use conversational language understanding with custom question answering?
Yes, you can use orchestration workflow to orchestrate between different conversational language understanding and question answering projects. Start by creating orchestration workflow projects, then connect your conversational language understanding and custom question answering projects. To perform this action, make sure that your projects are under the same Language resource.
How do I handle out of scope or domain utterances that aren't relevant to my intents?
Add any out of scope utterances to the none intent.
How do I control the none intent?
You can control the none intent threshold from UI through the project settings, by changing the none intent threshold value. The values can be between 0.0 and 1.0. Also, you can change this threshold from the APIs by changing the confidenceThreshold in settings object. Learn more about none intent
Is there any SDK support?
Yes, only for predictions, and samples are available for Python and C#. There's currently no authoring support for the SDK.
What are the training modes?
| Training mode | Description | Language availability | Pricing |
|---|---|---|---|
| Standard training | Faster training times for quicker model iteration. | Can only train projects in English. | Included in your pricing tier. |
| Advanced training | Slower training times using fine-tuned neural network transformer models. | Can train multilingual projects. | May incur added charges. |
For more information, see training modes.
Are there APIs for this feature?
Yes, all the APIs are available.