AI-102 Practice Test 39 — 15 Questions

Question 1

You are building a solution that uses Azure AI Language to analyze customer support transcripts. You need to detect personally identifiable information (PII) and also redact the detected PII from the text. Which TWO features should you use? (Select TWO.)

Accepted Answer

PII detection. Options A and C are correct. The PII detection feature identifies PII entities, and the redaction feature (available in the same API) can redact them. Option B is wrong because sentiment analysis is not for PII. Option D is wrong because key phrase extraction is not for PII. Option E is wrong because translation is not for PII detection or redaction.

Answer

Translation

Answer

Sentiment analysis

Answer

Key phrase extraction

Question 2

A healthcare organization uses Azure AI Language to extract medical entities from clinical notes. The solution must comply with HIPAA and redact protected health information (PHI). Which capability should the team configure?

Accepted Answer

Text Analytics for health. Option D is correct because the Azure AI Language health feature includes PHI detection and redaction. Option A is wrong because custom entity extraction does not automatically redact PHI. Option B is wrong because Azure Purview is for data governance, not real-time redaction. Option C is wrong because Azure AI Document Intelligence is for document processing, not language-specific PHI.

Answer

Azure Purview Information Protection

Answer

Custom named entity recognition (NER)

Answer

Azure AI Document Intelligence

Question 3

You need to translate a large volume of documents from English to French while preserving the original formatting. Which Azure service should you use?

Accepted Answer

Azure AI Translator (Document Translation). Option A is correct because Azure AI Translator supports document translation with formatting preservation. Option B is incorrect because Azure OpenAI can translate but may not preserve formatting. Option C is incorrect because Custom Translator is for custom models, not general translation. Option D is incorrect because Azure AI Language does not include translation.

Answer

Azure AI Language

Answer

Custom Translator in Azure AI Translator

Answer

Azure OpenAI Service with GPT-4

Question 4

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 5

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 6

Your application needs to extract key phrases from customer reviews to identify common topics. Which Azure AI Language feature should you use?

Accepted Answer

Key Phrase Extraction. Key Phrase Extraction is the correct feature for extracting key points from text. Entity Recognition extracts named entities. Sentiment Analysis determines sentiment. Language Detection identifies language.

Answer

Sentiment Analysis

Answer

Language Detection

Answer

Named Entity Recognition

Question 7

Refer to the exhibit. You are designing a Data Factory pipeline to perform sentiment analysis on a text column. The pipeline fails with a 'BadRequest' error. What is the most likely issue?

Accepted Answer

The input format is incorrect; it should be a JSON array of documents. The Cognitive Service activity expects a specific format for the input, typically a JSON structure with 'documents' array. The current input is just the text value, which is incorrect. The linked service name is correct. The activity type is appropriate. The output reference is not causing the error.

Answer

The output variable 'sentimentResult' is not defined

Answer

The activity type should be 'AzureFunction'

Answer

The linked service name is misspelled

Question 8

You want to use the Azure AI Language service to summarize long customer support conversations into a short summary. Which feature should you use?

Accepted Answer

Conversational Summarization. Option C is correct because Conversational Summarization is designed to summarize conversations between multiple participants. Option A is wrong because Key Phrase Extraction extracts key phrases, not a summary. Option B is wrong because Entity Extraction identifies entities. Option D is wrong because Sentiment Analysis determines sentiment, not a summary.

Answer

Sentiment Analysis

Answer

Entity Extraction

Answer

Key Phrase Extraction

Question 9

You are deploying a custom question answering solution in Azure AI Language. You need to ensure that the knowledge base can handle synonyms and alternative phrasings for questions. Which THREE strategies should you implement? (Select THREE.)

Accepted Answer

Add alternative question phrases to each QnA pair.. Options A, C, and D are correct. Adding alternative questions explicitly, using the synonym feature, and enabling active learning for suggestions all help handle synonyms and alternative phrasings. Option B is wrong because using a different project type is not a strategy for synonyms. Option E is wrong because increasing confidence threshold would reduce matches, not handle synonyms.

Answer

Use a custom question answering project type instead of the prebuilt one.

Answer

Increase the confidence threshold to 0.9 to reduce false positives.

Question 10

A developer is building a multilingual translation solution using Azure AI Translator. The solution must translate text to French, German, and Spanish. Which parameter should the developer set to specify the target language?

Accepted Answer

to. Option B is correct because the 'to' parameter specifies the target language. Option A is wrong because 'from' specifies source language. Option C is wrong because 'language' is not a REST API parameter. Option D is wrong because 'targetLanguage' is not the correct parameter name.

Answer

language

Answer

targetLanguage

Answer

from

Question 11

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 12

You need to analyze customer feedback to determine whether the sentiment is positive, negative, or neutral. Which Azure AI service should you use?

Accepted Answer

Azure AI Language - Sentiment Analysis. Azure AI Language provides Sentiment Analysis as a built-in feature. Language Detection, Key Phrase Extraction, and NER are different capabilities.

Answer

Azure AI Language - Key Phrase Extraction

Answer

Azure AI Language - Named Entity Recognition

Answer

Azure AI Language - Language Detection

Question 13

You are building a chatbot that must handle customer inquiries about order status. The solution must use Azure AI Language and support multiple languages. You need to configure the project to detect language automatically from user input. Which setting should you enable?

Accepted Answer

Enable multi-lingual detection in the project language settings.. Option B is correct because enabling multi-lingual detection in the language settings allows the project to automatically detect the input language. Option A is wrong because enabling only the primary language will not detect others. Option C is wrong because that setting is for spelling correction, not language detection. Option D is wrong because that setting is for conversation summarization.

Answer

Set the primary language to English only.

Answer

Use the conversation summarization feature.

Answer

Enable spelling correction in the project settings.

Question 14

Your company uses a custom question answering knowledge base in Azure AI Language to answer employee questions about HR policies. You need to update the knowledge base with a new set of FAQ documents that contain tables and images. What is the best way to ingest the new content?

Accepted Answer

Use Microsoft Foundry Copilot Studio to automatically ingest the documents into the knowledge base.. Option C is correct because Microsoft Foundry Copilot Studio can automatically ingest structured content from documents, including tables and images, into the knowledge base. Option A is wrong because manual QnA pairs are time-consuming and error-prone. Option B is wrong because the REST API can only add QnA pairs, not directly ingest documents. Option D is wrong because Azure AI Search is for indexing, not for adding content to the knowledge base.

Answer

Use Azure AI Search to index the documents and then import the index into the knowledge base.

Answer

Manually add the new QnA pairs using the Language Studio portal.

Answer

Use the Azure AI Language REST API to add the new QnA pairs programmatically.

Question 15

Refer to the exhibit. You are configuring an Azure AI Language resource using an ARM template. The settings include PII recognition with domain set to 'phi'. What is the effect of this setting?

Accepted Answer

It will detect protected health information (PHI) such as medical record numbers.. Option C is correct. The 'phi' domain setting in PII recognition configures the service to detect protected health information (PHI) as per HIPAA. Option A is wrong because 'phi' is specifically for health information, not general PII. Option B is wrong because 'phi' does not ignore PII categories; it focuses on health-related ones. Option D is wrong because the domain setting does not affect entity recognition.

Answer

It will detect all standard PII categories plus additional health-specific entities.

Answer

It will enable the entity recognition model to detect health entities.

Answer

It will ignore PII detection and only detect health-related entities.