Discover the essential next steps after creating a Conversational Language Understanding (CLU) project in Azure Language Studio. Learn how to build schemas, label utterances, and prepare for the AI-102 certification exam with practical insights!
Table of Contents
Question
Your organization, Xerigon Corporation, is developing a voice-activated customer service application. The application will accurately recognize and respond to customer intents, including “check order status,” “cancel an order,” and “speak to a representative.”
To achieve this, you have decided to implement Azure AI’s Conversational Language Understanding (CLU).
You have successfully created a CLU project using Language Studio and are ready to move to the next step in building your intent recognition solution.
After creating the CLU project in Language Studio, what should you typically do next?
A. Build a schema, and label utterances.
B. Gather additional utterance samples.
C. Train the model.
D. Deploy the model.
Answer
A. Build a schema, and label utterances.
Explanation
You would typically build a schema and label utterances in the given scenario. This schema serves as the foundation for your model. Labeling utterances involves tagging examples of a user’s text input or query with the correct intents and entities. Building the schema and labeling utterances are key steps before training the model. The schema is a combination of intents and entities. You can add intents and entities using Language Studio (as shown in the exhibit).
You would label each utterance by associating it with the correct intent and tagging any relevant entities within the utterance. For example, for the utterance “I want to check the status of my order,” you would label it with the “CheckOrderStatus
” intent and tag “OrderNumber” if mentioned.
You can label utterances using Language Studio (as shown in the exhibit).
Training the model is not typically the next step in the given scenario. Training the model is an essential step, but it comes after the schema has been built and the utterances labeled. Without a properly structured schema and well-labeled data, the model will not learn effectively during training.
Gathering additional utterance samples is not typically the next step in the given scenario. Gathering additional utterance samples can be useful for enhancing the model. However, it happens during the data collection phase before the project is created.
Deploying the model is not typically the next step in the given scenario. Deployment is the final step in the process, where you make your trained and tested model available for use in your application. However, deployment should only occur after the model has been trained and evaluated. Skipping ahead to deployment without completing the necessary prior steps will result in a poorly performing model.
Microsoft Azure AI Engineer Associate AI-102 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Engineer Associate AI-102 exam and earn Microsoft Azure AI Engineer Associate AI-102 certification.