AI-102 Practice Test 43 — 15 Questions

Question 1

You are using Azure AI Language Service to extract key phrases from customer reviews. You notice that for reviews containing the word 'not good', the service sometimes extracts 'good' as a key phrase. What is the most likely reason?

Accepted Answer

Key phrase extraction does not consider negation. Option B is correct because the key phrase extraction model does not perform sentiment analysis; it extracts phrases based on frequency and relevance, ignoring negation. Option A is wrong because the language model is accurate for most languages. Option C is wrong because prebuilt models are generally robust. Option D is wrong because the service does not have a parameter to exclude negative phrases.

Answer

The language detection model misidentified the language

Answer

You need to set a confidence threshold to exclude negative phrases

Answer

The service is not trained on your specific domain

Question 2

You are building a knowledge mining solution using Azure AI Search with AI enrichment. Which TWO built-in skills can be used to extract information from images embedded in documents?

Accepted Answer

Image Analysis skill. Options A and D are correct. OCR skill extracts text from images. Image Analysis skill extracts visual features (captions, tags). Option B is wrong because Entity Recognition skill works on text. Option C is wrong because Key Phrase Extraction works on text. Option E is wrong because Text Translation works on text.

Answer

Entity Recognition skill

Answer

Key Phrase Extraction skill

Answer

Text Translation skill

Question 3

You need to implement a solution that searches through a collection of scanned invoices and extracts invoice numbers, dates, and total amounts. The solution must run on a schedule without manual intervention. Which Azure service should you use?

Accepted Answer

Azure AI Document Intelligence. Option A is correct because Azure AI Document Intelligence is designed for extracting structured data from documents. Option B is for AI model deployment, not extraction. Option C is for indexing data for search. Option D is for conversational AI.

Answer

Azure Bot Service

Answer

Azure AI Search with built-in skills

Answer

Azure AI Foundry model catalog

Question 4

Your company has a large collection of legal contracts in PDF format stored in Azure Blob Storage. You need to extract key clauses, parties, and effective dates using a custom model in Azure AI Document Intelligence. The model must be retrained monthly as new contract templates are added. What is the recommended approach to handle model versioning and retraining?

Accepted Answer

Train a new model version using the 'compose' operation or copy the existing model and retrain with new samples. Option C is correct because Azure AI Document Intelligence allows training a new model version from an existing model using supervised training, preserving previously learned patterns. Option A is inefficient; Option B is not a feature; Option D is not supported.

Answer

Use a multi-model ensemble by training separate models per template

Answer

Retrain the model from scratch each month using all historical data

Answer

Use Azure Machine Learning pipelines to automate retraining and deploy a new endpoint

Question 5

You review the configuration for an Azure AI Search indexer. The indexer runs successfully but no documents are indexed. What is the most likely cause?

Accepted Answer

The indexer does not have a skillset or field mappings to populate the 'content' field from the blob. Option A is correct because the indexer does not specify a skillset or a field mapping to extract content; without a skillset, the blob content is not automatically mapped to the 'content' field unless default mappings exist. But here, the default content field mapping is not explicitly set, and the index expects a 'content' field but the blob's content is not automatically mapped if the indexer is not using a parsing mode. Option B is wrong because the connection string is valid. Option C is wrong because the container name is correct. Option D is wrong because maxFailedItems = -1 allows all failures.

Answer

The connection string in the data source is invalid

Answer

The container name is incorrect

Answer

The maxFailedItems parameter is set to -1, which causes the indexer to skip all documents

Question 6

Your organization is using Azure AI Document Intelligence to process a mix of invoices and purchase orders. You need to ensure that documents are correctly classified before extraction. Which THREE steps should you take?

Accepted Answer

Create a custom classification model in Document Intelligence. Options A, B, and D are correct. A: Create a custom classification model to differentiate document types. B: Label at least 5 samples per class to train the classifier. D: Use the classification model as part of a composed model or in a workflow. Option C is wrong because prebuilt models are for extraction, not classification. Option E is wrong because training with only one sample is insufficient.

Answer

Train the classification model with one sample per type

Answer

Use the prebuilt invoice and purchase order models for classification

Question 7

You need to extract key-value pairs from scanned forms as part of a knowledge mining solution. Which Azure AI service should you use?

Accepted Answer

Azure AI Document Intelligence. Azure AI Document Intelligence (formerly Form Recognizer) is designed to extract key-value pairs from forms. Option B is incorrect because Vision is for OCR, not structure. Option C is incorrect because Language is for text analysis. Option D is incorrect because Search is for indexing.

Answer

Azure AI Vision

Answer

Azure AI Language

Answer

Azure AI Search

Question 8

Which THREE components are required to build a knowledge mining solution using Azure AI Search that extracts and enriches content from PDF files?

Accepted Answer

Index. Option A is correct because a data source defines where to pull data. Option C is correct because an index stores the enriched content. Option E is correct because a skillset defines the enrichment pipeline. Option B is wrong because an indexer is required, but a datasource and index are separate components; an indexer connects them. Option D is wrong because a semantic configuration is optional.

Answer

Semantic configuration

Question 9

You are reviewing a skillset definition for an Azure AI Search indexer. The indexer is configured to index 1000 PDF documents. After running the indexer, you notice that only 500 documents have sentiment scores. What is the most likely cause?

Accepted Answer

The SplitSkill outputs are not correctly mapped to the SentimentSkill input; the skill runs only on the first page of each document. Option B is correct because the SplitSkill splits the document into pages, and the SentimentSkill runs per page. If the split output is not properly mapped, sentiment only runs on the first page. Option A is wrong because the skill order is correct (split before sentiment). Option C is wrong because the skill version is V3, which is valid. Option D is wrong because the context is correct.

Answer

The skills are defined in the wrong order; sentiment should run before split

Answer

The SentimentSkill is not supported in this region

Answer

The context of the SentimentSkill should be "/document" instead of "/document/pages/*"

Question 10

You are designing a solution to extract customer names and addresses from scanned handwritten forms. The forms are stored as images in Azure Blob Storage. The extraction must achieve high accuracy with minimal manual review. Which combination of Azure AI services should you use?

Accepted Answer

Azure AI Document Intelligence with a custom model trained on handwritten forms. Option D is correct because Document Intelligence's custom model can be trained on handwritten forms, and Language Service can be used to post-process entities. However, the best approach is to use Document Intelligence with a custom model trained on handwriting. Option A is wrong because Computer Vision OCR does not handle handwriting well. Option B is wrong because Language Service alone cannot extract from images. Option C is wrong because Form Recognizer (Document Intelligence) prebuilt models are not optimized for handwriting.

Answer

Azure AI Document Intelligence with prebuilt invoice and receipt models

Answer

Azure AI Language Service with custom Named Entity Recognition (NER)

Answer

Azure AI Computer Vision with OCR and Azure AI Search

Question 11

You are building a knowledge mining solution using Azure AI Search. You need to ensure that sensitive information such as credit card numbers is automatically removed from the indexed content. Which built-in skill should you add to your skillset?

Accepted Answer

PII Detection skill. Option B is correct because the Text Translation skill does not handle sensitive data. Option C is correct because the Entity Recognition skill can detect entities but not redact. The correct skill is Text Analytics for health, but for PII redaction, use the PII detection skill (part of Azure AI Language). However, among the options, the correct one is not listed directly. Assuming the correct answer is the 'Text Analytics for PII' skill, but since it's not an option, the closest is 'Entity Recognition' which can detect but not redact. The question may be outdated. For the sake of this exercise, Option A is correct because the 'Conditional skill' can be used to conditionally redact, but that is not built-in. Actually, the built-in skill for PII redaction is 'PII detection' (preview). In the official skills, there is 'PII detection skill'. So I'll set Option D as correct.

Answer

Entity Recognition skill

Answer

Conditional skill

Answer

Text Translation skill

Question 12

You are building an Azure AI Search solution that indexes data from multiple sources, including SQL Database and Azure Blob Storage. The index must be updated within 15 minutes of any source change. Which approach should you use to achieve near-real-time indexing?

Accepted Answer

Use the push API to send updates as soon as data changes. Option B is correct because the push API allows you to send updates directly to the index, providing near-real-time indexing. Option A is wrong because indexer-based scheduled indexing has a minimum interval of 5 minutes, and changes may not be picked up immediately. Option C is wrong because incremental enrichment is for AI enrichment, not for data updates. Option D is wrong because semantic search does not affect update frequency.

Answer

Enable incremental enrichment on the skillset

Answer

Use an indexer with a schedule set to run every 5 minutes

Answer

Enable semantic search to speed up indexing

Question 13

You are reviewing an index definition created with PowerShell. The index is used for a knowledge mining solution that extracts people and organizations from documents. Users report that when they type partial names in the search bar, the suggester does not return suggestions. What is the most likely reason?

Accepted Answer

The suggester sourceFields do not include people or organizations. Option C is correct because the suggester's sourceFields only include "content", not the "people" or "organizations" fields. Users likely want suggestions from those entity fields. Option A is wrong because the key field is required and correct. Option B is wrong because the suggester mode is valid. Option D is wrong because the fields are correctly defined as collections.

Answer

The people and organizations fields should be Edm.String instead of Collection(Edm.String)

Answer

The id field is not defined as a key in the index

Answer

The suggester searchMode should be 'analyzingInfixMatching' which is incorrect

Question 14

You are building an Azure AI Search solution to index a collection of technical manuals. Users need to find documents by searching for specific terms and also have the ability to filter by document category. Which feature should you configure in the index to support filtering?

Accepted Answer

Set the 'filterable' property to true on the category field. Option A is correct because filterable fields in Azure AI Search allow filtering of search results. Option B is wrong because facetable enables drill-down navigation, not direct filtering. Option C is wrong because sortable does not enable filtering. Option D is wrong because searchable determines full-text search, not filtering.

Answer

Set the 'facetable' property to true on the category field

Answer

Set the 'searchable' property to true on the category field

Answer

Set the 'sortable' property to true on the category field

Question 15

You are using Azure AI Search to index a set of PDF documents. The index includes a 'content' field with the extracted text. Users report that when they search for 'budget forecast', documents containing only 'budget' or 'forecast' are ranked lower than expected. Which configuration change would improve the ranking for multi-word queries?

Accepted Answer

Enable semantic search on the index. Option B is correct because enabling semantic search improves ranking by understanding the context of multi-word queries. Option A is wrong because adding more fields does not directly improve ranking for multi-word queries. Option C is wrong because setting a higher boost on 'content' does not fix the issue of missing proximity. Option D is wrong because changing the analyzer to a different language may not help.

Answer

Add a separate field for each word in the document

Answer

Change the analyzer to a custom analyzer that splits on spaces only

Answer

Set the 'content' field to a higher boosting value