Table of Contents
Question
You are building a Language Understanding model for an e-commerce business.
You need to ensure that the model detects when utterances are outside the intended scope of the model.
What should you do?
A. Export the model
B. Add utterances to the None intent
C. Create a prebuilt task entity
D. Create a new model
Answer
B. Add utterances to the None intent
Explanation
The correct answer is B. Add utterances to the None intent.
A Language Understanding model is trained to recognize the intents and entities of user utterances. An intent is the goal or action that the user wants to achieve, and an entity is a detail or parameter that is relevant to the intent. For example, in the utterance “I want to buy a blue shirt”, the intent is to buy something, and the entity is a blue shirt.
However, not all utterances are related to the intended scope of the model. For example, if the user says “What is the weather today?”, this is not a valid intent for an e-commerce business. To handle these cases, the model should have a None intent, which is a special intent that captures all utterances that are outside the scope of the model. By adding utterances to the None intent, the model can learn to distinguish between relevant and irrelevant utterances, and respond accordingly.
Option A is incorrect because exporting the model does not affect how it detects out-of-scope utterances. Exporting the model allows you to download it as a JSON file or publish it to an endpoint for integration with other services.
Option C is incorrect because creating a prebuilt task entity does not affect how the model detects out-of-scope utterances. A prebuilt task entity is a predefined entity that can recognize common types of information, such as numbers, dates, locations, etc. Creating a prebuilt task entity can help the model extract more information from the utterances, but it does not help the model identify when an utterance is irrelevant.
Option D is incorrect because creating a new model does not affect how the existing model detects out-of-scope utterances. Creating a new model requires defining new intents and entities, and training the model with new data. This can be useful if you want to create a different scope for your model, but it does not help the existing model handle out-of-scope utterances.
Reference
- Conversational Language Understanding None Intent – Azure AI services | Microsoft Learn
- What are intents in LUIS – Azure AI services | Microsoft Learn
- Compréhension du langage courant Intention None – Azure AI services | Microsoft Learn
- Frequently Asked Questions – Azure AI services | Microsoft Learn
- Build a Language Understanding model – Training | Microsoft Learn
- Conversational Language Understanding | Microsoft Azure
Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.
