AI-102 Implement natural language processing solutions Practice Test 7 — 15 Questions

Question 1

You deploy the ARM template shown in the exhibit. After deployment, you need to allow access to the Language service from your on-premises application. What should you do?

Accepted Answer

Add an IP rule with your on-premises public IP address.. Option D is correct because with 'Deny' as default action, you must add a virtual network rule or IP rule to allow access. Option A is incorrect because changing the SKU does not affect network access. Option B is incorrect because enabling firewall with 'Deny' blocks all, so you must add an exception. Option C is incorrect because custom subdomain is for endpoint, not access control.

Answer

Remove the customSubDomainName property.

Answer

Set the defaultAction to Allow.

Answer

Change the SKU to F0 to allow public access.

Question 2

You submit the request shown in the exhibit to the Azure AI Language service. What will the response contain?

Accepted Answer

Both key phrases and sentiment scores.. Option C is correct because the request includes two tasks: KeyPhraseExtraction and SentimentAnalysis, so the response will contain key phrases and sentiment scores. Option A is incorrect because it only mentions key phrases. Option B is incorrect because it only mentions sentiment. Option D is incorrect because it mentions entities which are not requested.

Answer

Only extracted key phrases.

Answer

Entity recognition results and sentiment scores.

Answer

Only sentiment scores.

Question 3

Your company uses Azure AI Language to analyze customer feedback. You need to extract key phrases from reviews in multiple languages. Which feature should you use?

Accepted Answer

Key phrase extraction. Key phrase extraction is the correct feature for identifying main points in text. Sentiment analysis detects positive/negative tone, entity recognition identifies named entities, and language detection identifies the language.

Answer

Named entity recognition

Answer

Language detection

Answer

Sentiment analysis

Question 4

You are building a chatbot using Azure AI Language and need to handle user intents that are not covered by the predefined intents. What should you implement?

Accepted Answer

A 'None' intent in a conversational language understanding project. A 'None' intent in a conversational language understanding (CLU) project captures utterances that do not match any defined intent, allowing the bot to respond appropriately. Fallback is a general term, and custom entities are not intents.

Answer

Custom entities to capture unknown phrases

Answer

A fallback intent in the QnA Maker knowledge base

Answer

A prebuilt intent from the LUIS catalog

Question 5

Your organization uses Azure AI Language for custom text classification. You have deployed a model to a dedicated endpoint. After updating the training data, you retrain and redeploy the model. Users report that the endpoint still returns predictions from the old model. What is the most likely cause?

Accepted Answer

The new model is not yet deployed; you must deploy it to the endpoint. The endpoint might still be pointing to the old trained model. You need to update the endpoint assignment to the new model version. Rebuilding the project or deleting the endpoint would be disruptive. Caching doesn't apply in this context.

Answer

The training data changes are not saved

Answer

The project needs to be rebuilt from scratch

Answer

The endpoint has a caching issue

Question 6

Which TWO Azure AI services can be used to perform sentiment analysis on text?

Accepted Answer

Azure AI Language. Azure AI Language is the primary service for sentiment analysis. Azure AI Translator can also detect sentiment as part of its translation capabilities. Azure AI Search and Azure AI Bot Service do not perform sentiment analysis natively.

Answer

Azure AI Search

Answer

Azure AI Bot Service

Answer

Azure AI Content Safety

Question 7

Which THREE components are required to build a custom question answering solution using Azure AI Language?

Accepted Answer

A project in Azure AI Language. A custom question answering project requires a project in Azure AI Language, a knowledge base containing Q&A pairs, and an endpoint for inference. A LUIS app is for language understanding, not QnA. An Azure AI Bot Service is optional for deploying a bot.

Answer

A Language Understanding (LUIS) app

Answer

An Azure AI Bot Service resource

Question 8

Your organization uses Azure AI Language to analyze customer support tickets. You need to ensure that personally identifiable information (PII) is detected and redacted before further processing. Which TWO features should you use?

Accepted Answer

Redaction. PII detection identifies personal data in text. Entity linking and key phrase extraction do not detect PII. Conversation summarization is not for PII.

Answer

Entity linking

Answer

Conversation summarization

Answer

Key phrase extraction

Question 9

You deploy an Azure AI Services resource using the ARM template shown in the exhibit. You need to test the Language service API from your local machine. What should you do first?

Accepted Answer

Add your public IP address to the ipRules array in the networkAcls. The template sets network access to Deny with no IP rules, blocking all traffic. You must add your public IP address to the ipRules array to allow access. Disabling network ACLs globally or using managed identity won't help if network access is denied.

Answer

Configure a managed identity for the resource

Answer

Change the defaultAction to Allow

Answer

Use Azure CLI to enable the resource

Question 10

A PowerShell script (exhibit) attempts to update the endpoint for an Azure AI Language resource. What is the outcome of running this script?

Accepted Answer

The script fails because the property does not exist. The property path 'apiProperties.textAnalytics.documentEndpoint' is incorrect. The correct property for custom endpoint is not modifiable via this method; the script will fail because the property does not exist. The endpoint is set during creation and cannot be changed this way.

Answer

The script creates a new resource

Answer

The script changes the API version

Answer

The script updates the endpoint successfully

Question 11

You are designing a conversational AI solution using Microsoft Copilot Studio. The exhibit shows part of a topic configuration. What is the purpose of the 'triggers' section?

Accepted Answer

To define the conditions that activate the topic. Triggers define conditions that activate the topic, such as specific user utterances. Actions define the response. The trigger type 'Utterance' means the topic fires when a user says that phrase.

Answer

To define the response the bot sends

Answer

To define the authentication method

Answer

To define the entities to extract

Question 12

Your company uses Azure AI Document Intelligence to process invoices. You need to extract the invoice date and total amount. Which model should you use?

Accepted Answer

Prebuilt invoice model. The prebuilt invoice model is specifically trained to extract fields like invoice date and total amount from invoices. The layout model extracts text and tables, not specific fields; the general document model is for key-value pairs; the read model only extracts text.

Answer

Read model

Answer

Layout model

Answer

General document model

Question 13

You are building a custom named entity recognition (NER) model using Azure AI Language. After labeling 200 documents, you train the model and achieve 85% precision but only 60% recall. Which action is most likely to improve recall?

Accepted Answer

Increase the number of labeled documents, especially those containing the target entities. Recall is the ability to find all relevant instances. Adding more labeled examples with the target entities will help the model recognize more patterns. Increasing training hours doesn't guarantee improvement; adjusting confidence threshold lowers precision; using a different service is not necessary.

Answer

Lower the confidence threshold

Answer

Increase the training hours

Answer

Switch to a different Azure AI Language feature

Question 14

Which TWO components are required to create a custom text classification model in Azure AI Language?

Accepted Answer

A set of labeled documents. A custom text classification project requires a project in Azure AI Language and a set of labeled documents for training. A LUIS app and a QnA maker knowledge base are different services. An Azure Functions app is not required.

Answer

A QnA Maker knowledge base

Answer

A Language Understanding (LUIS) app

Answer

An Azure Functions app

Question 15

Your organization needs to analyze customer call transcripts to extract key insights, including sentiment, issues, and resolution. Which THREE Azure AI Language features should you use?

Accepted Answer

Custom named entity recognition. Conversation summarization summarizes call transcripts; custom NER can extract specific entities like issues and resolutions; sentiment analysis detects sentiment. Key phrase extraction and PII detection are not the primary needs.

Answer

Key phrase extraction

Answer

PII detection

AI-102 Implement natural language processing solutions Practice Test 7 — 15 Questions

Exhibit

AI-102 Implement natural language processing solutions Practice Test 7 — 15 Questions

Exhibit