HOTSPOT
-
Select the answer that correctly completes the sentence.
Show Answer
Correct Answer: Power Virtual Agents
Explanation: Power Virtual Agents provides a no-code interface for building conversational apps and chatbots using built-in natural language processing models, unlike the Bot Framework (code-first) or Azure Health Bot (healthcare-specific).
Question 35
HOTSPOT
-
You have a large dataset that contains motor vehicle sales data.
You need to train an automated machine learning (automated ML) model to predict vehicle sale values based on the type of vehicle.
Which task should you select? To answer, select the appropriate task in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Regression
Explanation: The target is vehicle sale values, which are continuous numeric amounts, so an automated ML regression task is appropriate.
Question 36
HOTSPOT -
Select the answer that correctly completes the sentence.
Show Answer
Correct Answer: confusion matrix
Explanation: A confusion matrix displays predicted vs. actual outcomes as counts of true/false positives and negatives, typically in a grid of 0/1 class labels.
Question 37
You are building a Language Understanding model for an e-commerce business.
You need to ensure that the model detects when utterances are outside the intended scope of the model.
What should you do?
A. Export the model
B. Add utterances to the None intent
C. Create a prebuilt task entity
D. Create a new model
Show Answer
Correct Answer: B
Explanation: To detect utterances that are outside the intended scope of a Language Understanding (LUIS / Azure Language Understanding) model, you should add representative out-of-scope examples to the None intent. The None intent is specifically designed to capture user inputs that do not match any defined intent, allowing the model to recognize and handle unsupported or irrelevant utterances appropriately. The other options do not help with out-of-scope detection.
Question 38
Which AI service can you use to extract intent from a user input such as “Call me back later”?
A. Azure Cognitive Search
B. Translator
C. Language
D. Speech
Show Answer
Correct Answer: C
Explanation: Extracting intent from a textual user utterance like "Call me back later" is a natural language understanding task. In Azure, this capability is provided by the Language service, specifically Conversational Language Understanding (formerly LUIS). The other options do not focus on intent detection: Cognitive Search indexes content, Translator translates text, and Speech focuses on speech-to-text or text-to-speech rather than intent extraction.
Question 39
Which type of natural language processing (NLP) entity is used to identify a phone number?
A. regular expression
B. machine-learned
C. list
D. Pattern.any
Show Answer
Correct Answer: A
Explanation: A phone number has a well-defined textual pattern (digits, optional separators, country codes). In NLP systems such as Azure LUIS, entities that are identified based on fixed string patterns are best handled using regular expression entities. Machine-learned entities are for variable, context-dependent values, list entities match predefined vocabularies, and Pattern.any is a placeholder within patterns rather than a detector itself.
Question 40
DRAG DROP -
You are designing a system that will generate insurance quotes automatically.
Match the Microsoft responsible AI principles to the appropriate requirements.
To answer, drag the appropriate principle from the column on the left to its requirement on the right. Each principle may be used once, more than once, or not at all.
NOTE: Each correct match is worth one point.
Show Answer
Correct Answer: A customer’s personal information must be visible only to staff involved in the decision-making process:
Privacy and security
The decision-making process must be recorded so staff can identify the reasoning behind a particular quote:
Transparency
The system must be accessible to customers who use screen readers or other assistive technology:
Inclusiveness
Explanation: Limiting access to personal data addresses protection and confidentiality (Privacy and security). Recording and explaining how decisions are made enables understanding and traceability of outcomes (Transparency). Designing systems usable with assistive technologies ensures people of different abilities can access them (Inclusiveness).
Question 41
You have a knowledge base of frequently asked questions (FAQ).
You create a bot that uses the knowledge base to respond to customer requests.
You need to identify what the bot can perform without adding additional skills.
What should you identify?
A. Register customer purchases.
B. Register customer complaints.
C. Answer questions from multiple users simultaneously.
D. Provide customers with return materials authorization (RMA) numbers.
Show Answer
Correct Answer: C
Explanation: A bot that is based solely on a knowledge base can retrieve and present predefined information to users. It can naturally handle multiple conversations in parallel without extra skills. Registering purchases, handling complaints, or issuing RMA numbers are transactional tasks that require integrations with backend systems or additional skills, which go beyond a simple knowledge-base bot.
Question 42
You need to create a clustering model and evaluate the model by using Azure Machine Learning designer.
What should you do?
A. Split the original dataset into a dataset for training and a dataset for testing. Use the testing dataset for evaluation.
B. Use the original dataset for training and evaluation.
C. Split the original dataset into a dataset for features and a dataset for labels. Use the features dataset for evaluation.
D. Split the original dataset into a dataset for training and a dataset for testing. Use the training dataset for evaluation.
Show Answer
Correct Answer: B
Explanation: Clustering is an unsupervised learning technique with no labels. In Azure Machine Learning designer, a clustering model is trained on the dataset and evaluated using the same dataset to compute clustering metrics (such as distances and assignments). There is no train/test split required for evaluation as in supervised learning.
Question 43
DRAG DROP -
You plan to use Azure Cognitive Services to develop a voice controlled personal assistant app.
Match the Azure Cognitive Services to the appropriate tasks.
To answer, drag the appropriate service from the column on the left to its description on the right. Each service may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
Select and Place:
Show Answer
Correct Answer: Convert a user’s speech to text: Speech
Identify a user’s intent: Language service
Provide a spoken response to the user: Speech
Explanation: Speech handles speech-to-text and text-to-speech. The Language service (Conversational Language Understanding) analyzes text to determine user intent. Translator Text is for text translation and is not required here.
$19
Get all 230 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.
