Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions

Microsoft AI-900 Exam - Topic 4 Question 10 Discussion

Your website has a chatbot to assist customers.You need to detect when a customer is upset based on what the customer types in the chatbot.Which type of AI workload should you use?
D) natural language processing
A) anomaly detection
B) semantic segmentation
C) regression

Microsoft AI-900 Exam - Topic 4 Question 10 Discussion

Actual exam question for Microsoft's AI-900 exam
Question #: 10
Topic #: 4
[All AI-900 Questions]

Your website has a chatbot to assist customers.

You need to detect when a customer is upset based on what the customer types in the chatbot.

Which type of AI workload should you use?

Show Suggested Answer Hide Answer
Suggested Answer: D

Natural language processing (NLP) is used for tasks such as sentiment analysis, topic detection, language detection, key phrase extraction, and document categorization.

Sentiment Analysis is the process of determining whether a piece of writing is positive, negative or neutral.


https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/natural-language-processing

Contribute your Thoughts:

0/2000 characters
Norah
7 months ago
Semantic segmentation? That seems off for this task.
upvoted 0 times
...
Willard
7 months ago
Wait, can a chatbot really detect emotions?
upvoted 0 times
...
Rikki
8 months ago
Nah, regression isn't the right fit here.
upvoted 0 times
...
Leatha
8 months ago
I think anomaly detection could work too.
upvoted 0 times
...
Antonio
8 months ago
Definitely natural language processing!
upvoted 0 times
...
Ricki
8 months ago
Regression seems off too; it’s usually for predicting numerical values, not analyzing text emotions.
upvoted 0 times
...
Stevie
8 months ago
I feel like semantic segmentation is more related to images, so that can't be right for this question.
upvoted 0 times
...
Gabriele
8 months ago
I'm not entirely sure, but I remember something about anomaly detection being used for identifying unusual patterns.
upvoted 0 times
...
Na
8 months ago
I think we might need to use natural language processing since we're dealing with customer text input.
upvoted 0 times
...
Ammie
8 months ago
This seems like a pretty straightforward question about the GENEX Probe and frequency locking modes. I'll need to carefully review the options to determine which one is not supported.
upvoted 0 times
...
Delisa
8 months ago
Okay, I've got it! The answer is D. Child datasets can be added to the root dataset to narrow down the search.
upvoted 0 times
...
Eugene
8 months ago
Hmm, this seems like a tricky one. I'll need to carefully review the options and think through the possible scenarios.
upvoted 0 times
...

Save Cancel