AI-103 Information Extraction — 20 Questions

Question 1

You are developing a custom extraction model using Azure AI Document Intelligence Studio. Your training dataset consists of multi-page invoices with varying structures, and some fields appear only on the final page. How should you structure your tagging configuration?

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

Accepted Answer

Tag the fields on whatever page they appear across the sample documents in Document Intelligence Studio.. Custom neural and template models support multi-page documents where fields can be tagged across any page of the document set during training.

Answer

Create a separate custom model for the final page and chain them using an orchestration model.

Answer

Split every multi-page invoice into individual single-page documents before uploading.

Answer

Define all late-appearing fields as optional metadata parameters in the training configuration JSON file.

Question 2

You are troubleshooting an Azure AI Document Intelligence custom extraction model. When you test a new document, certain currency values are being extracted with the currency symbol missing. Where should you look in the JSON response structure to find the normalized value?

Accepted Answer

In the documentFields array under the valueCurrency object property.. Document Intelligence extracts fields with both a raw text representation and a normalized value (e.g., currency, number, date) when applicable.

Answer

In the styles collection under the isHandwritten property.

Answer

In the paragraphs collection under the boundingRegions array.

Answer

In the analyzeResults object under the content property.

Question 3

You are configuring an Azure AI Document Intelligence orchestration model to automatically classify and extract data from incoming customer correspondence, which includes invoices, work orders, and purchase orders. One of the component models is failing to classify documents correctly. How should you resolve this issue?

Accepted Answer

Retrain the failing component custom model with more distinct sample documents that represent the specific document class.. Orchestration models rely on component custom models. If classification fails, you must retrain or refine the specific component model with distinct training samples.

Answer

Modify the orchestration model routing threshold in the Azure portal settings.

Answer

Switch the orchestration model from a template-based classifier to a neural classifier using the REST API.

Answer

Update the API version to bypass classification and force direct extraction via the general document model.

Question 4

Your team needs to extract data from a large volume of standardized tax forms using Azure AI Document Intelligence. The forms have a fixed layout where fields are always in the exact same location. Which model type provides the fastest training and highest accuracy for this specific use case?

Accepted Answer

Custom template model. Custom template models are optimized for forms with consistent visual structures and fixed layouts, requiring fewer training documents and providing high accuracy.

Answer

Prebuilt receipt model

Answer

Custom neural model

Answer

General document model

Question 5

You are configuring an Azure AI Document Intelligence prebuilt model to extract key-value pairs from standard invoices. Which API operation should your application call to process the document asynchronously?

Accepted Answer

POST /documentintelligence/documentModels/prebuilt-invoice:analyze?api-version=2024-02-29-preview. The prebuilt invoice model uses the document analysis feature via the analyzeDocument operation, passing the prebuilt-invoice model ID.

Answer

POST /documentintelligence/documentModels/prebuilt-invoice:train?api-version=2024-02-29-preview

Answer

POST /documentintelligence/models/prebuilt-invoice/analyze?api-version=2024-02-29-preview

Answer

POST /formrecognizer/v2.1/prebuilt/invoice/analyze

Question 6

You are integrating Azure AI Document Intelligence into a web application. You call the analyzeDocument API and receive a 202 Accepted response. What is the correct pattern for your application to retrieve the final extraction results?

Accepted Answer

Poll the URL provided in the Operation-Location response header until the status returns 'succeeded', then fetch the results.. Document Intelligence analysis is an asynchronous operation. You must poll the Operation-Location URL returned in the response header until the status is succeeded.

Answer

Wait for exactly 60 seconds and then send a GET request to the original analyze endpoint.

Answer

Immediately parse the response body of the 202 Accepted response for the extracted JSON data.

Answer

Open a WebSocket connection to the streaming endpoint specified in the WebSocket-Location header.

Question 7

Which prebuilt Azure AI Document Intelligence model should you use to extract line items, merchant name, transaction date, and total tax from point-of-sale purchase receipts?

Accepted Answer

prebuilt-receipt. The prebuilt receipt model (prebuilt-receipt) is specifically trained to extract data from sales receipts.

Answer

prebuilt-invoice

Answer

prebuilt-idDocument

Answer

prebuilt-businessCard

Question 8

You are building an Azure AI Document Intelligence solution to process complex financial statements. Due to varying layouts across different financial institutions, you decide to use a custom neural model instead of a custom template model. What is a key architectural advantage of the custom neural model in this scenario?

Accepted Answer

It supports cross-page tables and varying visual layouts without requiring strict coordinate alignment.. Custom neural models use deep learning to understand document structures without requiring exact visual template matching, making them robust to layout variations.

Answer

It requires significantly fewer training documents than a template model to achieve high accuracy.

Answer

It can be trained entirely unsupervised without requiring any human-labeled training documents.

Answer

It can extract data from scanned documents without running Optical Character Recognition (OCR) first.

Question 9

You are designing a high-throughput document processing pipeline using Azure AI Document Intelligence. To optimize latency and cost, you want to extract only the text and layout structures (paragraphs, lines, words, and tables) from a multi-page PDF without performing key-value extraction or using custom models. Which model ID should you specify in your API request?

Accepted Answer

prebuilt-layout. The prebuilt layout model (prebuilt-layout) extracts document structures, tables, selection marks, and text without entity or custom key-value extraction.

Answer

prebuilt-invoice

Answer

prebuilt-read

Answer

prebuilt-document

Question 10

You are using Azure AI Document Intelligence to extract information from identity documents, such as passports and driver licenses. Which prebuilt model should you select?

Accepted Answer

prebuilt-idDocument. The prebuilt ID document model (prebuilt-idDocument) is designed to extract fields from passports and driver licenses.

Answer

prebuilt-tax.us.w2

Answer

prebuilt-W2

Answer

prebuilt-businessCard

Question 11

Your company processes business cards from international clients. Which prebuilt Azure AI Document Intelligence model should you use to extract names, company names, emails, and phone numbers from these cards?

Accepted Answer

prebuilt-businessCard. The prebuilt business card model (prebuilt-businessCard) extracts contact information from business cards.

Answer

prebuilt-invoice

Answer

prebuilt-layout

Answer

prebuilt-receipt

Question 12

You are configuring a custom extraction model in Azure AI Document Intelligence and want to compose multiple specialized models into a single endpoint that automatically classifies and routes documents. Which REST API endpoint should you use to create this composed model?

Accepted Answer

POST /documentintelligence/documentModels:compose?api-version=2024-02-29-preview. Composed models (orchestration or composed models) are created using the documentModels:build or compose operations depending on the API version. Specifically, the compose operation combines multiple model IDs.

Answer

PUT /documentintelligence/documentModels/{modelId}?api-version=2024-02-29-preview

Answer

POST /documentintelligence/documentModels:train?api-version=2024-02-29-preview

Answer

POST /documentintelligence/models:classify?api-version=2024-02-29-preview

Question 13

You are implementing cross-domain document extraction where incoming PDFs contain complex nested tables with merged cells. You need to extract these tables accurately into structured JSON. Which capability of Azure AI Document Intelligence should you rely on?

Accepted Answer

The tables collection in the analyze result, which provides rowSpan, colSpan, and cell bounding regions.. Document Intelligence layout and custom models provide table extraction capabilities that identify row index, column index, span, and whether cells are headers or merged.

Answer

The documents collection, which converts tables into Markdown format automatically.

Answer

The keyValuePairs collection, which automatically flattens table rows into key-value pairs.

Answer

The styles collection, which identifies table gridlines through computer vision edge detection.

Question 14

You are training a custom template model in Azure AI Document Intelligence and notice that one of your key fields is consistently failing to extract on documents where the label text is vertically oriented. How should you address this issue?

Accepted Answer

Re-examine and ensure all instances of the field across training samples are accurately tagged with correct bounding regions in Document Intelligence Studio.. Document Intelligence supports reading text at various orientations, but custom template models rely on consistent visual labeling. Ensuring the labeling captures the correct bounding regions and retraining helps resolve orientation issues.

Answer

Switch the model type from custom template to prebuilt read model.

Answer

Set the queryParameters property to 'orientation=vertical' in the training API request body.

Answer

Rotate the source PDF documents to landscape orientation prior to uploading them for training.

Question 15

You are auditing an Azure AI Document Intelligence solution for data privacy compliance. Documents contain sensitive Personally Identifiable Information (PII). When using prebuilt models or custom models, how is data handled by Microsoft regarding model training?

Accepted Answer

Customer data and custom model training data are encrypted at rest and in transit, and are never used to train Microsoft foundation models.. Microsoft does not use customer data submitted to Azure AI Document Intelligence to train baseline prebuilt models or customer custom models.

Answer

Training data uploaded for custom models is made publicly available in the Azure AI gallery after 30 days.

Answer

Data privacy controls require you to deploy a local container, as cloud APIs store training documents indefinitely.

Answer

All submitted documents are automatically used to retrain the global prebuilt models overnight.

Question 16

You are building an automated invoice processing pipeline using Azure AI Document Intelligence. Some incoming invoices contain handwritten vendor signatures and handwritten approval dates. Which feature must you ensure is supported and enabled when configuring your analysis request?

Accepted Answer

Rely on the built-in OCR capability which detects both printed and handwritten text across supported models.. Document Intelligence automatically supports handwritten text detection, but understanding its performance implications on custom or prebuilt models is crucial for accuracy.

Answer

Enable the 'handwritten=true' query parameter in the API call header.

Answer

Train a custom neural model exclusively with handwritten signature samples.

Answer

Deploy a separate Azure AI Vision Handwritten Text container and pipe its output into the Document Intelligence request.

Question 17

You are configuring an Azure AI Document Intelligence container for deployment in an on-premises disconnected environment. Which environment variable is mandatory for the container to start successfully and report billing usage?

Accepted Answer

EULA=accept, billing=, apikey=. Disconnected containers require the billing endpoint and API key, along with accepting the license agreement.

Answer

AZURE_COGNITIVE_SERVICES_TENANT_ID

Answer

AZURE_AI_CONNECTOR_CONNECTION_STRING

Answer

DOCUMENT_INTELLIGENCE_MODEL_CACHE_DIR

Question 18

Which TWO prebuilt models are officially available in Azure AI Document Intelligence for extracting specialized domain data? (Choose TWO)

Accepted Answer

prebuilt-tax.us.w2. Azure AI Document Intelligence provides prebuilt models for W-2 tax forms and invoices, among others.

Answer

prebuilt-socialSecurityCard

Answer

prebuilt-architecturalDrawing

Answer

prebuilt-medicalChart

Question 19

When building a custom template model in Azure AI Document Intelligence Studio, which THREE types of data or attributes can you extract by labeling your training documents? (Choose THREE)

Accepted Answer

Tables (including row and column structures). Custom template models allow labeling fields, tables, and selection marks.

Answer

Facial biometric embeddings

Answer

Real-time audio transcription timestamps

Question 20

Which TWO file formats are natively supported as inputs for analysis in Azure AI Document Intelligence? (Choose TWO)

Accepted Answer

application/pdf. Document Intelligence supports standard document formats like PDF, JPEG, PNG, TIFF, and BMP.

Answer

text/html

Answer

application/zip

Answer

application/vnd.ms-excel