Microsoft AI-102 Exam - Topic 1 Question 3 Discussion

Actual exam question for Microsoft's AI-102 exam

Question #: 3
Topic #: 1

[All AI-102 Questions]

You are building a multilingual chatbot.

You need to send a different answer for positive and negative messages.

Which two Text Analytics APIs should you use? Each correct answer presents part of the solution. (Choose two.)

NOTE: Each correct selection is worth one point.

ALinked entities from a well-known knowledge base

BSentiment Analysis

CKey Phrases

DDetect Language

ENamed Entity Recognition

Show Suggested Answer

Suggested Answer: B, D

B: The Text Analytics API's Sentiment Analysis feature provides two ways for detecting positive and negative sentiment. If you send a Sentiment Analysis request, the API will return sentiment labels (such as 'negative', 'neutral' and 'positive') and confidence scores at the sentence and document-level.

D: The Language Detection feature of the Azure Text Analytics REST API evaluates text input for each document and returns language identifiers with a score that indicates the strength of the analysis.

This capability is useful for content stores that collect arbitrary text, where language is unknown. Reference:

https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to- sentiment-analysis?tabs=version-3-1

https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to- language-detection

by Donte at May 05, 2022, 09:39 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Shelba

4 months ago

I agree with B, but I’m not sure about C.

upvoted 0 times

...

Virgie

4 months ago

Wait, can Sentiment Analysis really handle that?

upvoted 0 times

...

Oretha

4 months ago

B is a must, but why not D?

upvoted 0 times

...

Benton

5 months ago

I think B is right, but A seems off.

upvoted 0 times

...

Martha

5 months ago

Definitely B and C!

upvoted 0 times

...

Carin

5 months ago

I’m leaning towards Sentiment Analysis and Named Entity Recognition, but I’m not sure if the latter is necessary for just positive or negative responses.

upvoted 0 times

...

Magnolia

5 months ago

I remember practicing a similar question, and I think Key Phrases could help identify the main sentiment, but I'm not entirely confident.

upvoted 0 times

...

Kristofer

5 months ago

I think we need to use Sentiment Analysis to determine if the message is positive or negative, but I'm not sure about the second API.

upvoted 0 times

...

Brendan

5 months ago

Sentiment Analysis definitely seems right, but I feel like Linked Entities might not be relevant here. Maybe Detect Language could be useful instead?

upvoted 0 times

...

Shanice

5 months ago

Hmm, the requirements seem pretty specific. I'm not sure which technology would be the best fit, but I'll try to eliminate the options that don't seem to fully meet the criteria.

upvoted 0 times

...

Sherron

5 months ago

Hmm, I'm not sure about this one. Restarting the VM seems like it could help, but I'm not confident that's the best approach. Maybe I should read through the options more carefully.

upvoted 0 times

...

Claribel

5 months ago

I think it's something about how the cardinality changes when records are added or removed, right? But I'm not entirely sure which option it is.

upvoted 0 times

...