AI-102 Practice Exam 57 — 20 Questions

Question 1

You are building a computer vision solution to detect defects on a manufacturing assembly line. The solution must process images in real-time with low latency, and you need to choose an Azure service. Which service should you use?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Azure Custom Vision. Azure Custom Vision is the correct choice because it allows you to train a custom image classification or object detection model tailored to detect specific manufacturing defects. It supports real-time, low-latency inference via a Docker container deployed to edge devices or directly through the prediction API, meeting the assembly line's performance requirements.

Answer

Azure Computer Vision API

Answer

Azure Video Indexer

Answer

Azure Form Recognizer

Question 2

A developer is building a mobile app that uses Azure Computer Vision to analyze images. The app needs to handle many requests with low latency. Which pricing tier should they choose?

Accepted Answer

Computer Vision S1 tier.. The Computer Vision S1 tier is designed for production workloads requiring high throughput and low latency, making it suitable for a mobile app that handles many image analysis requests. Unlike the Free F0 tier, which has strict rate limits (e.g., 20 transactions per minute), the S1 tier offers higher transactions per second (e.g., up to 10 TPS) and guaranteed performance for real-time scenarios.

Answer

Video Analyzer S1 tier.

Answer

Free F0 tier.

Answer

Custom Vision S0 tier.

Question 3

A team is developing a solution to automatically summarize long documents using Azure AI Language. Which feature should they use?

Accepted Answer

Extractive summarization.. Extractive summarization is the correct feature because it specifically identifies and extracts the most important sentences from a document to create a concise summary. Azure AI Language's extractive summarization uses a ranking model to score sentences based on relevance and informativeness, directly addressing the requirement to automatically summarize long documents.

Answer

Sentiment analysis.

Answer

Key phrase extraction.

Answer

Entity recognition.

Question 4

Which TWO actions should you take to ensure that an Azure AI Language Service custom entity recognition model complies with data privacy regulations?

Accepted Answer

Configure data retention policies to delete data after processing. Configuring data retention policies to delete data after processing ensures that personally identifiable information (PII) is not stored longer than necessary, which is a key requirement for compliance with regulations like GDPR and CCPA. Option E is correct because anonymizing or removing PII from training data prevents sensitive information from being embedded in the custom entity recognition model, reducing the risk of data leakage during inference.

Answer

Use prebuilt entity recognition models instead of custom

Answer

Increase the number of training epochs

Answer

Enable diagnostic logging for audit trails

Question 5

You need to analyze customer call transcripts to identify positive and negative sentiment. Which Azure AI Language feature should you use?

Accepted Answer

Sentiment Analysis. Sentiment Analysis is the correct Azure AI Language feature because it is specifically designed to evaluate text and determine whether the sentiment expressed is positive, negative, or neutral. For customer call transcripts, this feature analyzes each sentence or document and returns a sentiment label and confidence scores, directly addressing the requirement to identify positive and negative sentiment.

Answer

Language Detection

Answer

Named Entity Recognition

Answer

Key Phrase Extraction

Question 6

You are using the Azure AI Language service to process customer reviews. You need to extract the following insights: overall sentiment, key phrases, and entity types (such as product names). Which THREE operations should you call?

Accepted Answer

Key Phrase Extraction. Key Phrase Extraction is correct because it identifies the most important points in the text, such as product names or features, which directly supports extracting 'key phrases' from customer reviews. This operation is part of the Azure AI Language service's text analytics capabilities and is essential for summarizing review content.

Answer

Language Detection

Answer

PII Detection

Question 7

Which TWO actions can you take to improve the performance of a Conversational Language Understanding model?

Accepted Answer

Add more varied utterances to each intent.. Adding more varied utterances to each intent directly improves the model's ability to generalize and correctly classify user input by exposing it to a wider range of phrasing, synonyms, and sentence structures. This reduces overfitting to specific word patterns and increases the likelihood of accurate predictions on unseen data.

Answer

Reduce the number of intents.

Answer

Change the Azure region of the resource.

Answer

Disable active learning.

Question 8

Refer to the exhibit. You deploy this ARM template to create an Azure AI Language Service resource. After deployment, you try to call the Language Service API from your application but receive a 403 Forbidden error. What is the most likely cause?

Accepted Answer

The network ACLs block all traffic because no IP rules are defined. The ARM template in the exhibit does not include any IP rules in the network ACLs section, which means the default behavior for Azure AI Language Service is to deny all traffic when network ACLs are explicitly configured. Even though the resource is deployed successfully, the absence of allowed IP ranges or a virtual network rule causes the service to block all API calls, resulting in a 403 Forbidden error.

Answer

The SKU S0 does not support API calls from applications

Answer

The resource kind is set incorrectly for Language Service

Answer

The custom subdomain name is invalid

Question 9

A company uses Azure AI Speech for real-time captioning during live events. They notice a delay of 5 seconds between speech and caption display. Which action should they take to reduce latency?

Accepted Answer

Use the Speech SDK with intermediate results enabled. Enabling intermediate results in the Speech SDK allows the client to receive partial, real-time recognition hypotheses as the audio is being processed, rather than waiting for the final, fully processed result. This reduces the perceived latency from the full utterance duration (which can be several seconds) to near-instantaneous display of partial captions, directly addressing the 5-second delay.

Answer

Deploy a custom speech model

Answer

Switch to batch transcription API

Answer

Increase the maxAlternatives parameter

Question 10

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 Azure AI Language feature because it is specifically designed to identify and return a list of key phrases from unstructured text, such as customer reviews, that capture the main topics and themes. This allows you to aggregate common topics across multiple reviews without manual analysis.

Answer

Sentiment Analysis

Answer

Language Detection

Answer

Named Entity Recognition

Question 11

You need to translate a large batch of documents from English to multiple languages. Which Azure service should you use?

Accepted Answer

Azure AI Translator. Azure AI Translator is the correct service because it is specifically designed for batch document translation across multiple languages, supporting both text and document translation with source language auto-detection. It provides a dedicated Document Translation feature via the Translator API, which can handle large volumes of files asynchronously while preserving document structure and formatting.

Answer

Conversational Language Understanding

Answer

Azure AI Language Detection

Answer

Azure AI Speech Translation

Question 12

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 ARM template in the exhibit sets `defaultAction` to `Deny`, which blocks all traffic not explicitly allowed by the `ipRules` array. To test the Language service API from your local machine, you must add your public IP address to the `ipRules` array so that the resource's network firewall permits inbound requests from your IP. Without this step, all API calls from your local machine will be rejected with a 403 Forbidden error.

Answer

Configure a managed identity for the resource

Answer

Change the defaultAction to Allow

Answer

Use Azure CLI to enable the resource

Question 13

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 14

You are developing a custom text classification model using Azure AI Language. You have labeled 2000 documents across 10 categories. You need to evaluate the model's performance before deploying to production. Which THREE metrics should you examine?

Accepted Answer

Recall. Recall is correct because it measures the proportion of actual positive instances correctly identified by the model, which is critical in custom text classification to ensure that relevant documents are not missed. In Azure AI Language, recall helps assess how well the model captures all instances of each category, especially when class distribution is imbalanced across the 10 categories.

Answer

Word Error Rate

Answer

BLEU Score

Question 15

A company uses Azure AI Speech to transcribe customer service calls. They need to identify callers by name and account number. Which feature should be enabled?

Accepted Answer

Custom speech model. A custom speech model is required because the company needs to recognize specific domain terms like caller names and account numbers, which are not part of the default base speech model. By training a custom speech model with relevant audio and text data, Azure AI Speech can accurately transcribe these specialized terms, improving recognition accuracy for the call center scenario.

Answer

Speaker recognition

Answer

Pronounciation assessment

Answer

Batch transcription

Question 16

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

Accepted Answer

Entity Linking. Entity Linking (C) and Named Entity Recognition (E) are both Azure AI Language features designed to extract structured data from unstructured text. Entity Linking disambiguates entities by linking them to a knowledge base (e.g., Wikipedia), providing a unique identifier and structured metadata. Named Entity Recognition identifies and categorizes entities (e.g., person, organization, location) directly from text, enabling extraction of structured information.

Answer

Sentiment Analysis

Answer

Language Detection

Answer

Key Phrase Extraction

Question 17

You are deploying a knowledge mining solution using Azure AI Search and Azure AI Document Intelligence. The solution must extract text from scanned documents, identify named entities, and index the content. You need to configure the skillset. Which TWO built-in skills should you include in the skillset?

Accepted Answer

OCR skill. The OCR skill extracts text from scanned images. The EntityRecognition skill identifies named entities. The Merge skill is not required because OCR output is already text. The KeyPhraseExtraction skill extracts key phrases, not entities. The LanguageDetection skill detects language, not entities.

Answer

Merge skill

Answer

LanguageDetection skill

Answer

KeyPhraseExtraction skill

Question 18

Refer to the exhibit. You are using Azure AI Search with a skillset that splits documents into pages and then analyzes sentiment per page. You notice that the sentiment analysis is returning unexpected results, such as positive sentiment for negative content. What is the most likely cause?

Accepted Answer

The page split mode with overlap may still cut sentences, causing sentiment to be evaluated on incomplete sentences.. The SplitSkill uses 'pages' mode which often splits at page boundaries, potentially cutting sentences in half. This can cause the sentiment analysis to receive incomplete text, leading to incorrect sentiment. Option A is not the primary issue. Option B is about the initial text, not splitting. Option C is about the split context, but the sentiment context is correct.

Answer

The SentimentSkill is receiving the entire document text instead of individual pages.

Answer

The split skill context '/document' should be '/document/content'.

Answer

The defaultLanguageCode is set to 'en' but the documents contain other languages.

Question 19

Which TWO Azure AI services can be used together to build a knowledge mining solution that extracts text from handwritten notes and indexes them for search?

Accepted Answer

Azure AI Search. Azure AI Search (A) is the correct service because it provides the indexing and querying capabilities required for a knowledge mining solution. Azure AI Vision's Read API (C) is correct because it extracts printed and handwritten text from images, which is the first step in making handwritten notes searchable. Together, they form a pipeline where the Read API extracts text, and Azure AI Search indexes that extracted text for full-text search.

Answer

Azure AI Document Intelligence

Answer

Azure AI Language

Answer

Azure AI Translator

Question 20

A company is planning to use Azure AI Document Intelligence to extract data from invoices. The solution must handle variations in invoice formats. Which TWO actions should be taken to improve accuracy?

Accepted Answer

Include samples of different layouts in the training set.. Including samples of different invoice layouts in the training set enables the custom model to learn variations in structure, field placement, and formatting. This improves the model's ability to generalize across diverse invoice formats, reducing extraction errors. Azure AI Document Intelligence custom models require labeled training data to adapt to specific document types, and diverse samples directly address format variability.

Answer

Avoid using custom models; rely on prebuilt models only.

Answer

Use a large number of unlabeled samples.

Answer

Use a single prebuilt model for all invoices.