Cyber Monday 2024! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions

Microsoft Exam AI-102 Topic 4 Question 52 Discussion

Actual exam question for Microsoft's AI-102 exam
Question #: 52
Topic #: 4
[All AI-102 Questions]

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.

After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.

You have a chatbot that uses question answering in Azure Cognitive Service for Language.

Users report that the responses of the chatbot lack formality when answering random questions that are outside the scope of the knowledge base.

You need to ensure that the chatbot provides formal responses to these spurious questions.

Solution: From Language Studio, you modify the question and answer pairs for the custom intents, and then retrain and republish the model.

Does this meet the goal?

Show Suggested Answer Hide Answer
Suggested Answer: B

Contribute your Thoughts:

Erin
8 months ago
I'm with Ashlee on this one. Retraining the model is a logical step, and it could really help improve the formality of the responses. Although, I do wonder if there might be some other tweaks we could make to the language model as well. Maybe we should explore a few different options.
upvoted 0 times
...
Ashlee
8 months ago
Hmm, I don't know. Modifying the training data seems like a valid solution to me. If the responses are lacking in formality, then updating the question and answer pairs could be the way to go. Plus, it's a straightforward approach that's easy to implement.
upvoted 0 times
...
Carisa
8 months ago
Yeah, I agree with Nida. Retraining the model might be overkill for this problem. I think we should try some simpler approaches first, like adjusting the tone or adding some formal language templates to the responses.
upvoted 0 times
...
Nida
8 months ago
I'm not sure about this one. Modifying the question and answer pairs seems like a lot of work, and I'm not convinced it will actually make the responses more formal. Shouldn't we be looking at the language model itself, rather than just the training data?
upvoted 0 times
...

Save Cancel
az-700  pass4success  az-104  200-301  200-201  cissp  350-401  350-201  350-501  350-601  350-801  350-901  az-720  az-305  pl-300  

Warning: Cannot modify header information - headers already sent by (output started at /pass.php:70) in /pass.php on line 77