AI-102 Implement natural language processing solutions Practice Test 4 — 15 Questions

Question 1

Which ONE Azure AI service can be used to perform sentiment analysis on text?

Accepted Answer

Azure AI Language. Azure AI Language provides built-in sentiment analysis capabilities as part of its natural language processing (NLP) features, allowing you to assess the sentiment (positive, negative, neutral, or mixed) of text at the document and sentence level. Azure AI Translator does not include sentiment analysis; it only provides text translation. Therefore, only Azure AI Language is correct.

Answer

Azure AI Search

Answer

Azure AI Bot Service

Answer

Azure AI Translator

Answer

Azure AI Content Safety

Question 2

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. Option C (PII detection) is correct because Azure AI Language's Personally Identifiable Information (PII) feature is specifically designed to identify entities such as names, addresses, phone numbers, email addresses, and social security numbers in text, which is exactly what is needed to find PII in customer support tickets. Option B (Redaction) is correct because the PII detection feature supports a redaction policy that replaces detected PII with asterisks or a specified placeholder (for example, using the redaction parameter set to 'redaction=entity' or 'redaction=characterMask'), thereby removing the sensitive data before further processing. Option A (Entity linking) is not correct because it only disambiguates entities to a knowledge base like Wikipedia and does not detect or remove PII. Option D (Conversation summarization) is not correct because it produces summaries of conversations and does not identify or redact PII. Option E (Key phrase extraction) is not correct because it extracts main talking points and does not detect or redact PII.

Answer

Entity linking

Answer

Conversation summarization

Answer

Key phrase extraction

Question 3

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 PowerShell script attempts to set the 'endpoint' property on an existing Azure AI Language resource using the `Set-AzCognitiveServicesAccount` cmdlet. However, the 'endpoint' property is read-only and cannot be modified after resource creation; it is generated automatically by Azure based on the resource's name and region. Attempting to update it results in a failure because the property does not exist as a writable attribute in the resource's schema.

Answer

The script creates a new resource

Answer

The script changes the API version

Answer

The script updates the endpoint successfully

Question 4

Your team uses Azure AI Language in a multi-region architecture. You need to ensure that the solution is resilient to regional outages. Which THREE actions should you take?

Accepted Answer

Use a global endpoint that routes to the nearest region. Option B is correct because Azure AI Language supports a global endpoint that automatically routes requests to the nearest available region, which helps maintain service continuity if a region becomes unavailable. Option C is correct because configuring a load balancer (such as Azure Traffic Manager or Azure Front Door) across regional Azure AI Language endpoints distributes requests and can fail over traffic when a region is down. Option D is correct because deploying Azure AI Language resources in multiple regions provides the redundant regional endpoints that a resilient multi-region architecture requires. Option A is not correct because disabling regional endpoints removes the ability to target specific regions and does not by itself improve resilience. Option E is not correct because relying on a single region, even with high availability enabled, does not protect against a regional outage.

Answer

Disable regional endpoints

Answer

Use a single region with high availability enabled

Question 5

You are deploying a custom Named Entity Recognition (NER) model using Azure AI Language. You have 500 labeled documents. After training, the model shows high precision but low recall. Which action is most likely to improve recall?

Accepted Answer

Add more labeled examples covering the missed entities. Adding more labeled examples that cover the missed entities directly addresses the root cause of low recall: the model has not seen enough representative patterns for those entities during training. In Azure AI Language custom NER, the model learns to recognize entities based on the labeled data; insufficient or imbalanced examples for certain entity types cause the model to fail to identify them, lowering recall. Enriching the training set with diverse examples of the underperforming entities gives the model more opportunities to learn their variations, thereby improving recall without sacrificing precision.

Answer

Switch to Conversational Language Understanding

Answer

Reduce the confidence threshold for entity extraction

Answer

Increase the number of training epochs

Question 6

You are using Azure AI Translator to translate documents from English to French. Some technical terms must remain untranslated. How should you handle this?

Accepted Answer

Provide a dictionary with the terms and their translations set to the same word. Azure AI Translator allows you to provide a custom dictionary where you can map a source term to a target term. By setting the translation to the same word (e.g., 'API' → 'API'), the service will leave that term untranslated while still translating the rest of the document. This is the native, supported mechanism for preserving specific terms without post-processing or custom model training.

Answer

Set the includeUntranslated parameter to true

Answer

Train a custom translation model that ignores those terms

Answer

Post-process the output to revert translations of those terms

Question 7

You are using Azure AI Language to analyze medical records. The built-in NER model does not recognize some medical terms. What should you do?

Accepted Answer

Train a custom NER model using Azure AI Language. Custom NER allows training a model on your specific terms. Text Analytics for Health is a specialized built-in model for healthcare but may not cover all custom terms. Custom Text Classification is for document classification. Entity Linking disambiguates to a knowledge base.

Answer

Use the Text Analytics for Health feature

Answer

Use Entity Linking

Answer

Use Custom Text Classification

Question 8

Which TWO Azure AI Language features can you use to extract structured data from unstructured text?

Accepted Answer

Entity Linking. Entity Linking (option C) is correct because it takes unstructured text and returns structured data in the form of identified entities plus their resolved references to a knowledge base (e.g., a Wikipedia URL and entity ID), which is exactly structured output extracted from free text. Named Entity Recognition (option E) is also correct because it parses unstructured text and returns structured entities categorized by type (such as Person, Organization, Location, DateTime, Quantity), each with position offsets and confidence scores. Sentiment Analysis (option A) is not correct here because it returns sentiment labels and confidence scores (positive/negative/neutral/mixed) rather than structured entity data. Language Detection (option B) is not correct because it only returns the detected language name and ISO 639-1 code for the text. Key Phrase Extraction (option D) is not correct because it returns a list of salient phrases, which is unstructured keyword output rather than structured, typed data with resolved references.

Answer

Sentiment Analysis

Answer

Language Detection

Answer

Key Phrase Extraction

Question 9

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.. Azure AI Language's multi-lingual detection setting enables the project to automatically identify the language of user input without requiring explicit language selection. This is essential for a chatbot handling customer inquiries in multiple languages, as it allows the service to route the input to the appropriate language-specific model or processing pipeline, ensuring accurate order status responses across languages.

Answer

Set the primary language to English only.

Answer

Use the conversation summarization feature.

Answer

Enable spelling correction in the project settings.

Question 10

You are developing a multilingual chatbot that must understand user intents in English, Spanish, and French. You are using the Azure AI Language service with a Conversational Language Understanding (CLU) project. What is the recommended approach to handle multiple languages?

Accepted Answer

Add utterances in all three languages to the CLU project and enable multi-lingual detection.. The Azure AI Language service's Conversational Language Understanding (CLU) supports multi-lingual projects natively. By adding utterances in English, Spanish, and French to a single CLU project and enabling multi-lingual detection, the model learns to recognize intents across languages without needing separate projects or translation steps. This approach leverages the underlying multilingual BERT-based model, which shares language-agnostic representations, making it the recommended and most efficient method.

Answer

Use Azure AI Translator to translate all input to English before sending to CLU.

Answer

Use the Translator service to detect language and route to language-specific CLU endpoints.

Answer

Create separate CLU projects for each language.

Question 11

You need to build a solution that can answer questions based on a set of PDF documents, such as product manuals. The solution should allow users to ask questions in natural language and receive answers with citations. Which Azure AI service should you use?

Accepted Answer

Azure AI Custom Question Answering. Azure AI Custom Question Answering (part of Azure AI Language) is specifically designed to extract question-answer pairs from semi-structured content like PDFs and provide answers with citations. It uses a deep learning-based extractive QA model that can locate answer spans within documents and return the source text as a citation, directly meeting the requirement for natural language questions and cited answers from product manuals.

Answer

Azure AI Text Analytics

Answer

Azure Cognitive Search

Answer

Azure AI Document Intelligence (formerly Form Recognizer)

Question 12

You are building a chat bot that uses Azure AI Language to process customer support tickets. The bot must extract entities like order numbers (e.g., ORD-12345) and issue categories. You need to choose the best approach for entity extraction to minimize development effort and ensure high accuracy.

Accepted Answer

Create a custom named entity recognition (NER) project in Azure AI Language that includes prebuilt components for order numbers and trains custom models for categories.. Azure AI Language's custom named entity recognition (NER) allows you to combine prebuilt components (like regex-based order number patterns) with custom-trained models for issue categories, minimizing development effort while achieving high accuracy. This approach leverages the built-in entity extraction capabilities of Azure AI Language without requiring intent classification or complex pipeline orchestration.

Answer

Leverage the Text Analytics for Health API to extract entities from the support tickets.

Answer

Use the Prebuilt Entity Extraction skill in Azure AI Search to extract order numbers and categories from the text.

Answer

Use the Conversational Language Understanding (CLU) project type to train a model for both intent and entity extraction.

Question 13

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 the Azure AI Language REST API to add the new QnA pairs programmatically.. The Azure AI Language REST API allows programmatic ingestion of new QnA pairs, including those extracted from documents with tables and images. It supports batch operations and can handle complex content by parsing and structuring it appropriately. This is the most efficient and scalable method for updating a knowledge base with a new set of FAQ documents.

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 Microsoft Foundry Copilot Studio to automatically ingest the documents into the knowledge base.

Question 14

You are using Azure AI Language to analyze customer reviews. You need to identify specific aspects (e.g., 'price', 'service') and their associated sentiment. Which feature should you use?

Accepted Answer

Aspect-based sentiment analysis. Aspect-based sentiment analysis (C) is the correct feature because it specifically identifies individual aspects (e.g., 'price', 'service') within text and determines the sentiment associated with each aspect. In Azure AI Language, this is implemented via the 'Sentiment Analysis' API with opinion mining enabled, which extracts targets (aspects) and their corresponding assessments (opinions) to provide granular sentiment scores per aspect.

Answer

Opinion Mining

Answer

Sentiment Analysis

Answer

Key Phrase Extraction

Question 15

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. PII detection (Option A) is correct because it is the Azure AI Language feature specifically designed to identify categories of personally identifiable information such as names, addresses, phone numbers, and social security numbers within text. PII redaction (Option D) is correct because it is the companion feature that replaces the detected PII entities with placeholder tokens (e.g., '********') or masks them, enabling safe sharing of transcripts. Together, they fulfill the requirement to both detect and redact PII from customer support transcripts.

Answer

Translation

Answer

Sentiment analysis

Answer

Key phrase extraction