Extract Information with Azure Content Understanding in Foundry Tools AI-102 Practice Questions (Page 7)

Questions 31–35

1. 31application · medium

   A legal firm has a repository of contract documents. They want to automatically generate a short executive summary for each contract and also identify the contract type (e.g., NDA, employment, lease) and the parties involved. They plan to use Azure Content Understanding in Foundry Tools. What should they build?

   • AA pipeline that classifies documents into predefined categories and then uses the category name as the summary without further processing.
   • BA pipeline that only performs OCR to extract all text and then uses a separate language model to generate the summary and identify the contract type.
   • CA pipeline that only extracts tables from the contracts to find the parties and contract type, and then summarizes the table content.
   • DA single pipeline that performs document classification, entity extraction for party names, and summarization, then outputs the summary and extracted metadata.
   Reveal Solution Discussion Select an answer first
2. 32application · medium

   An insurance company processes claim forms that include a photo of the damage, a handwritten signature, and a printed policy number. They want to extract the policy number, verify the signature exists, and save the photo for further analysis. Using Azure Content Understanding in Foundry Tools, what should they configure?

   • AA summarization pipeline that describes the claim and includes the policy number in the summary.
   • BA custom extraction pipeline with OCR, an attribute for policy number, an attribute for signature presence, and image extraction.
   • CA document classification pipeline that categorizes the claim and extracts the policy number.
   • DA table extraction pipeline that treats the policy number and signature as table cells.
   Reveal Solution Discussion Select an answer first
4. 33foundation · easy

   What is the purpose of document classification in Azure Content Understanding?

   • ATo extract text from images
   • BTo summarize document content
   • CTo extract entities like names and dates
   • DTo assign documents to predefined categories
   Reveal Solution Discussion Select an answer first
5. 34application · medium

   A real estate agency receives property listing forms that are scanned images. They need to extract the property address, listing price, and the agent's name from each form. The forms have a consistent layout. What should they use in Azure Content Understanding?

   • AAn image extraction pipeline that extracts the form as an image and then uses OCR to read the text manually.
   • BA summarization pipeline that generates a summary of the form, from which the address and price can be read.
   • CA custom entity extraction pipeline with OCR enabled, defining entities for address, price, and agent name.
   • DA document classification pipeline that categorizes the form as a property listing and then uses the category to infer the address and price.
   Reveal Solution Discussion Select an answer first
6. 35application · medium

   A government agency processes permit applications that include a photo ID, a signed declaration, and a printed application number. They need to extract the application number, verify the signature is present, and classify the application as 'approved' or 'pending'. Using Azure Content Understanding in Foundry Tools, what should they configure?

   • AA summarization pipeline that summarizes the application and includes the application number.
   • BA custom pipeline with attribute detection for application number and signature, and document classification for status.
   • CA table extraction pipeline to pull the application number from any tables on the form.
   • DAn OCR pipeline to read the application and then manually classify and verify the signature.
   Reveal Solution Discussion Select an answer first