Microsoft AI-102 Practice Test - Questions Answers, Page 7
List of questions
Question 61

You are training a Language Understanding model for a user support system.
You create the first intent named GetContactDetails and add 200 examples.
You need to decrease the likelihood of a false positive.
What should you do?
Active learning is a technique of machine learning in which the machine learned model is used to identify informative new examples to label. In LUIS, active learning refers to adding utterances from the endpoint traffic whose current predictions are unclear to improve your model.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-glossary
Question 62

DRAG DROP
You are building a Language Understanding model for purchasing tickets.
You have the following utterance for an intent named PurchaseAndSendTickets.
Purchase [2 audit business] tickets to [Paris] [next Monday] and send tickets to [[email protected]]
You need to select the entity types. The solution must use built-in entity types to minimize training data whenever possible.
Which entity type should you use for each label? To answer, drag the appropriate entity types to the correct labels. Each entity type may be used once, more than once, or not at all.
You may need to drag the split bar between panes or scroll to view content.
Box 1: GeographyV2
The prebuilt geographyV2 entity detects places. Because this entity is already trained, you do not need to add example utterances containing GeographyV2 to the application intents.
Box 2: Email
Email prebuilt entity for a LUIS app: Email extraction includes the entire email address from an utterance. Because this entity is already trained, you do not need to add example utterances containing email to the application intents.
Box 3: Machine learned
The machine-learning entity is the preferred entity for building LUIS applications.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-reference-prebuilt-geographyv2
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-reference-prebuilt-email
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/reference-entity-machine-learned-entity
Question 63

You need to build a chatbot that meets the following requirements:
Supports chit-chat, knowledge base, and multilingual models
Performs sentiment analysis on user messages
Selects the best language model automatically
What should you integrate into the chatbot?
Language Understanding: An AI service that allows users to interact with your applications, bots, and IoT devices by using natural language.
QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information.
Text Analytics: Mine insights in unstructured text using natural language processing (NLP)βno machine learning expertise required. Gain a deeper understanding of customer opinions with sentiment analysis. The Language Detection feature of the Azure Text Analytics REST API evaluates text input
Incorrect Answers:
A, B, D: Dispatch uses sample utterances for each of your botβs different tasks (LUIS, QnA Maker, or custom), and builds a model that can be used to properly route your userβs request to the right task, even across multiple bots.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/overview/overview
Question 64

Your company wants to reduce how long it takes for employees to log receipts in expense reports. All the receipts are in English. You need to extract top-level information from the receipts, such as the vendor and the transaction total. The solution must minimize development effort. Which Azure Cognitive Services service should you use?
Azure Form Recognizer is a cognitive service that lets you build automated data processing software using machine learning technology. Identify and extract text, key/value pairs, selection marks, tables, and structure from your documents βthe service outputs structured data that includes the relationships in the original file, bounding boxes, confidence and more.
Form Recognizer is composed of custom document processing models, prebuilt models for invoices, receipts, IDs and business cards, and the layout model.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer
Question 65

You are developing a new sales system that will process the video and text from a public-facing website.
You plan to monitor the sales system to ensure that it provides equitable results regardless of the user's location or background.
Which two responsible Al principles provide guidance to meet the monitoring requirements? Each correct answer presents part of the solution. (Choose two.)
NOTE: Each correct selection is worth one point.
AI systems should treat all people fairly.
AI systems should perform reliably and safely.
Reference:
https://docs.microsoft.com/en-us/azure/cloud-adoption-framework/strategy/responsible-ai
Question 66

You have the following C# method for creating Azure Cognitive Services resources programmatically.
You need to call the method to create a free Azure resource in the West US Azure region. The resource will be used to generate captions of images automatically.
Which code should you use?
Many of the Cognitive Services have a free tier you can use to try the service. To use the free tier, use F0 as the SKU for your resource. There are two tiers of keys for the Custom Vision service. You can sign up for a F0 (free) or S0 (standard) subscription through the Azure portal.
Incorrect Answers:
A: There is no free tier (F0) for ComputerVision.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-apis-create-account-client-library?pivots=programming-language-csharp
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/limits-and-quotas
Question 67

You successfully run the following HTTP request.
POST https://management.azure.com/subscriptions/18c51a87-3a69-47a8-aedc-a54745f708a1/resourceGroups/RG1/providers/Microsoft.CognitiveServices/accounts/contosol/regenerateKey? api-version=2017-04-18
Body{"keyName": "Key2"}
What is the result of the request?
https://docs.microsoft.com/en-us/rest/api/searchmanagement/2021-04-01-preview/query- keys/create
Question 68

You build a custom Form Recognizer model.
You receive sample files to use for training the model as shown in the following table.
Which three files can you use to train the model? Each correct answer presents a complete solution. (Choose three.)
NOTE: Each correct selection is worth one point.
Question 69

A customer uses Azure Cognitive Search.
The customer plans to enable a server-side encryption and use customer-managed keys (CMK) stored in Azure. What are three implications of the planned change? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
Reference:
https://docs.microsoft.com/en-us/azure/search/search-security-overview
Question 70

You are developing a new sales system that will process the video and text from a public-facing website. You plan to notify users that their data has been processed by the sales system.
Which responsible Al principle does this help meet?
Reference:
https://docs.microsoft.com/en-us/azure/cloud-adoption-framework/strateqy/responsible-ai
Question