Microsoft AI-102 Exam - Topic 1 Question 2 Discussion

Actual exam question for Microsoft's AI-102 exam

Question #: 2
Topic #: 1

You are building a bot on a local computer by using the Microsoft Bot Framework. The bot will use an existing Language Understanding model.

You need to translate the Language Understanding model locally by using the Bot Framework CLI. What should you do first?

AFrom the Language Understanding portal, clone the model.

BExport the model as an .lu file.

CCreate a new Speech service.

DCreate a new Language Understanding service.

Show Suggested Answer

Suggested Answer: B

You might want to manage the translation and localization for the language understanding content for your bot independently.

Translate command in the @microsoft/bf-lu library takes advantage of the Microsoft text translation API to automatically machine translate .lu files to one or more than 60+ languages supported by the Microsoft text translation cognitive service.

What is translated?

An .lu file and optionally translate Comments in the lu file

LU reference link texts

List of .lu files under a specific path.

https://github.com/microsoft/botframework-cli/blob/main/packages/luis/docs/translate-command.md

by Norah at May 04, 2022, 06:56 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Cecily

4 months ago

Seems like exporting is the right move, but I'm not 100% sure.

upvoted 0 times

...

Dalene

4 months ago

I thought cloning from the portal was the first step?

upvoted 0 times

...

Ciara

4 months ago

Wait, why would you need a new Speech service for this?

upvoted 0 times

...

Anika

5 months ago

Totally agree, option B is the way to go!

upvoted 0 times

...

Carlee

5 months ago

You need to export the model as an .lu file first!

upvoted 0 times

...

Claudia

5 months ago

I’m leaning towards exporting the model as an .lu file, but I could be mixing it up with another topic we covered.

upvoted 0 times

...

Sue

5 months ago

I feel like creating a new Language Understanding service could be necessary, but it seems like it might be too early in the process.

upvoted 0 times

...

Dewitt

5 months ago

I think we need to export the model as an .lu file first, but I'm not entirely sure if that's the only step.

upvoted 0 times

...

Yolando

5 months ago

I remember practicing a similar question, and I think cloning the model from the portal might be the right move.

upvoted 0 times

...

Maryanne

5 months ago

Hmm, this seems straightforward. I think the answer is A - Executive summary.

upvoted 0 times

...

Argelia

5 months ago

I'm a bit confused by the wording of this question. I'll have to re-read it a few times to make sure I understand.

upvoted 0 times

...

Pearly

5 months ago

Okay, let's see. I know the ORACLE_DATAPUMP driver is used for data movement, so I'm guessing the answer has to do with that.

upvoted 0 times

...

Antione

5 months ago

Okay, let's see. The options are shared resource pooling gains, lower complexity, common off-the-shelf hardware, and far edge cloud deployments for 5G core UPF. I'm pretty confident that D is the correct answer, since that's actually a reason to use Cloud RAN, not a reason not to.

upvoted 0 times

...