Azure Cognitive Service for Language でカスタムの質問応答プロジェクトを開発します。このプロジェクトはチャットボットで使用されます。マルチターンの会話に対応できるようにプロジェクトを構成する必要があります。どうすればよいでしょうか?
正解:A
Comprehensive Detailed Explanation
When you develop a custom question answering project (formerly QnA Maker, now part of Azure Cognitive Service for Language - Question Answering), you can configure it for multi-turn conversations.
Follow-up prompts
Used to create multi-turn conversations.
They allow the system to present additional questions to the user after an initial question, guiding the conversation flow.
Example:
User: " Tell me about Azure Storage. "
Bot: " Which type of storage: Blob, File, Queue, or Table? "
These follow-up options are configured using follow-up prompts.
Correct choice for this question.
Active learning
Helps improve the knowledge base by suggesting alternative questions from user queries.
Not related to multi-turn conversation flow.
Alternate questions
Used to add different phrasings for the same question.
Example: "What is Azure Blob Storage?" and "Explain Blob Storage in Azure." This improves recognition but does not enable multi-turn conversations.
Chit-chat
Adds small talk and casual conversation handling (e.g., greetings, jokes).
Not related to multi-turn Q & A about a knowledge base.
The answer: A. Add follow-up prompts
Microsoft References
Multi-turn conversations in Question Answering
Add follow-up prompts in Question Answering