Microsoft Certified: Azure AI Engineer AssociateImplement knowledge mining solutionsMedium
A legal firm is using Azure AI Document Intelligence to process contracts. They frequently encounter specific clauses that are not easily identified by pre-built models due to unique legal jargon and formatting variations. The firm needs a solution to accurately extract these custom clauses. Which Document Intelligence model type should they use?
- APre-built Layout model
- BGeneral Document model
- CPre-built Invoice model
- DCustom extraction model
Show answer & explanationAnswer & explanation
Correct answer: D. Custom extraction model
Custom extraction models in Azure AI Document Intelligence allow users to train a model on their own specific documents to extract unique fields, tables, and clauses that pre-built models might not recognize. This is ideal for specialized document types like legal contracts with unique jargon.
Why the other options are wrong
- A. The pre-built Layout model extracts text, tables, and structure but doesn't understand custom semantic fields like specific clauses.
- B. The General Document model extracts key-value pairs and entities from general documents but may struggle with highly specialized, uniquely formatted clauses.
- C. The pre-built Invoice model is tailored for invoices and would not be effective for legal contracts.
Document Intelligence Custom Extraction Model
A Document Intelligence model trained by users on their own documents to extract specific data fields, tables, or structures unique to their business needs.
- Requires labeled training data (typically 5+ documents).
- Ideal for specialized document types or unique data extraction.
- Provides high accuracy for user-defined fields.
Memory trick: For unique documents, you need a 'custom model' to 'teach' the AI what to look for.