Extract Information with Azure Content Understanding in Foundry Tools AI-102 Practice Questions (Page 2)

Questions 6–10

1. 6application · medium

   A hospital receives patient intake forms that can be either 'new patient' or 'follow-up'. They need to classify each form, extract the patient ID and visit date, and detect whether a consent checkbox is marked. Using Azure Content Understanding in Foundry Tools, what should they configure?

   • AA custom pipeline with document classification, entity extraction for patient ID and date, and attribute detection for the checkbox.
   • BA summarization pipeline that summarizes the form and includes the patient ID and date.
   • CA table extraction pipeline to pull the patient ID and date from any tables on the form.
   • DAn OCR pipeline to read the form and then manually classify and extract fields.
   Reveal Solution Discussion Select an answer first
2. 7foundation · easy

   What is the purpose of table extraction in Azure Content Understanding?

   • ATo extract text from images
   • BTo classify documents
   • CTo extract tables from documents to retrieve structured data
   • DTo summarize documents
   Reveal Solution Discussion Select an answer first
4. 8application · medium

   An insurance company receives customer emails with attached documents that could be claims, policy change requests, or cancellation notices. They need to automatically route each document to the correct processing queue and also extract the policy number and the date of the request. The documents are scanned images and PDFs. What should they implement in Azure Content Understanding in Foundry Tools?

   • AAn OCR pipeline that extracts all text and then uses keyword search to find 'claim', 'policy change', or 'cancellation' to route the document.
   • BA summarization pipeline that generates a summary of each document and uses the summary to determine the queue and extract the policy number.
   • CAn entity extraction pipeline that extracts all entities and then manually maps them to the correct queue based on the entity types.
   • DA document classification pipeline that categorizes each document and also extracts the policy number and date as custom fields, with OCR enabled.
   Reveal Solution Discussion Select an answer first
5. 9expert · hard

   A multinational corporation processes vendor contracts that are in multiple languages. They need to extract the contract parties, effective date, and governing law from each contract. They also need to classify each contract as 'renewable' or 'non-renewable' and generate a short summary. The contracts are a mix of scanned images and native PDFs. They have a limited budget and want to minimize the number of pipelines to maintain. What should they do in Azure Content Understanding?

   • ACreate separate pipelines for scanned images and native PDFs, each with entity extraction and classification, and then combine the results.
   • BCreate a single pipeline that uses OCR, custom entity extraction for parties, date, and governing law, classification for renewable status, and summarization.
   • CUse a document classification pipeline to classify the contract type and then use the classification label as the summary and extract entities from the label.
   • DUse a pre-built entity extraction model for legal entities and then manually classify and summarize each contract.
   Reveal Solution Discussion Select an answer first
6. 10foundation · easy

   In Azure Content Understanding, what is the primary purpose of creating an OCR pipeline?

   • ATo extract text from images and documents for further processing
   • BTo classify documents into predefined categories
   • CTo summarize long documents into key points
   • DTo detect and extract tables from documents
   Reveal Solution Discussion Select an answer first