nerdexam
Microsoft

AI-102 · Question #59

Drag and Drop Question You are using a Language Understanding service to handle natural language input from the users of a web-based customer agent. The users report that the agent frequently…

The correct answer is Enable active learning.; Validate the utterances logged for review and modify the model.; Train and republish the Language Understanding model. The correct sequence addresses the problem systematically: first, Enable Active Learning so LUIS can automatically capture and flag real user utterances that it is uncertain about for review. Second, Validate the utterances logged for review and modify the model by reviewing…

Submitted by yuki_2020· Mar 30, 2026Build and manage a conversational AI solution / Implement natural language understanding with Azure Cognitive Services Language Understanding (AI-102 or AI-900)

Question

Drag and Drop Question You are using a Language Understanding service to handle natural language input from the users of a web-based customer agent. The users report that the agent frequently responds with the following generic response: "Sorry, I don't understand that." You need to improve the ability of the agent to respond to requests. Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. (Choose three.) Answer:

Exhibit

AI-102 question #59 exhibit

Answer Area

Drag items

Add prebuilt domain models as required.Validate the utterances logged for review and modify the model.Migrate authoring to an Azure resource authoring key.Enable active learning.Enable log collection by using Log Analytics.Train and republish the Language Understanding model.

Correct arrangement

  • Enable active learning.
  • Validate the utterances logged for review and modify the model.
  • Train and republish the Language Understanding model.

Explanation

The correct sequence addresses the problem systematically: first, Enable Active Learning so LUIS can automatically capture and flag real user utterances that it is uncertain about for review. Second, Validate the utterances logged for review and modify the model by reviewing those captured utterances, labeling them correctly, and incorporating them to improve intent/entity coverage. Third, Train and republish the Language Understanding model so the improvements are applied and the updated model is deployed to production - directly reducing the 'Sorry, I don't understand that' responses.

Topics

#Language Understanding (LUIS)#Active Learning#Natural Language Processing#Model Improvement

Community Discussion

No community discussion yet for this question.

Full AI-102 Practice