Microsoft Exam AI-102 Topic 5 Question 68 Discussion

Actual exam question for Microsoft's AI-102 exam

Question #: 68
Topic #: 5

[All AI-102 Questions]

You train a Conversational Language Understanding model to understand the natural language input of users.

You need to evaluate the accuracy of the model before deploying it.

What are two methods you can use? Each correct answer presents a complete solution.

NOTE: Each correct selection is worth one point.

AFrom the language authoring REST endpoint, retrieve the model evaluation summary.

BFrom Language Studio, enable Active Learning, and then validate the utterances logged for review.

CFrom Language Studio, select Model performance.

DFrom the Azure portal, enable log collection in Log Analytics, and then analyze the logs.

Show Suggested Answer

Suggested Answer: B

by Cristal at Jul 09, 2024, 09:14 AM

Limited Time Offer

25%

Off

Get Premium AI-102 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Stephanie

5 days ago

Hmm, I'm not sure about option A. Retrieving the model evaluation summary from a REST endpoint sounds a bit technical and not very user-friendly. I'd prefer something more visually intuitive, like option C in Language Studio.

upvoted 0 times

...

Gayla

7 days ago

Option B seems like the way to go. Active Learning is a great way to validate the model's performance and get real-time feedback from users. Plus, it's right there in Language Studio - no need to dig through the Azure portal!

upvoted 0 times

...

Adell

8 days ago

I prefer option B and option C. Active Learning in Language Studio can help improve the model's understanding, and selecting Model performance will give us a clear view of its accuracy.

upvoted 0 times

...

Noel

13 days ago

I agree with Winifred. Option A will give us a summary of the model evaluation, and option D will help us analyze the logs for further insights.

upvoted 0 times

...

Winifred

16 days ago

I think we can use option A and option D to evaluate the accuracy of the model.

upvoted 0 times

...