exam questions

Exam AI-900 All Questions

View all questions & answers for the AI-900 exam

Exam AI-900 topic 1 question 128 discussion

Actual exam question from Microsoft's AI-900
Question #: 128
Topic #: 1
[All AI-900 Questions]

You have a webchat bot that provides responses from a QnA Maker knowledge base.
You need to ensure that the bot uses user feedback to improve the relevance of the responses over time.
What should you use?

  • A. key phrase extraction
  • B. sentiment analysis
  • C. business logic
  • D. active learning
Show Suggested Answer Hide Answer
Suggested Answer: D 🗳️

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
RRJMkNxo
Highly Voted 1 year, 11 months ago
Active learning. 1.Bot gets the answer from the knowledge base with the GenerateAnswer API, using the top property to get a number of answers. 2.Bot determines explicit feedback: Using your own custom business logic, filter out low scores. In the bot or client-application, display list of possible answers to the user and get user's selected answer. 3.Bot sends selected answer back to QnA Maker with the Train API.
upvoted 21 times
kzue
1 year, 5 months ago
this is a good procedure to embed active learning. I would enhance is to collect multiple user hits before retraining the model. User may (un)intentionally select the wrong response and as a bot designer you have to make sure the quality stays high (responsible AI!).
upvoted 1 times
...
...
catalene
Highly Voted 1 year, 10 months ago
Yes Active learning
upvoted 5 times
...
rdemontis
Most Recent 1 week ago
Selected Answer: D
Answer is correct. Active learning is a technique where the system actively selects certain samples from the user interactions and prompts the user to provide feedback on the relevance or correctness of the response. This feedback is then used to update and refine the model, improving its performance over time. By incorporating active learning into the bot's workflow, you can collect feedback from users and leverage it to continually train and fine-tune the model. This iterative process helps the bot learn from user interactions, identify areas for improvement, and deliver more accurate and relevant responses in the future. https://learn.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/use-active-learning
upvoted 3 times
...
Amrden
1 year, 6 months ago
True answer
upvoted 1 times
...
omw2wealth
1 year, 10 months ago
ow that's new
upvoted 5 times
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
Loading ...
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago