Microsoft Certified: Azure AI Engineer AssociateImplement natural language processing solutionsMedium
A financial institution wants to categorize incoming customer emails into predefined categories such as 'Loan Application', 'Account Inquiry', or 'Fraud Report'. The volume of emails is very high, and accuracy is critical. Which Azure AI Language feature should be used to automate this classification process?
- ANamed Entity Recognition (NER)
- BCustom Text Classification
- CSentiment Analysis
- DKey Phrase Extraction
Show answer & explanationAnswer & explanation
Correct answer: B. Custom Text Classification
Custom Text Classification is specifically designed to train a model to categorize text into custom-defined labels based on provided examples. This is ideal for assigning specific categories like 'Loan Application' or 'Fraud Report' to a high volume of emails.
Why the other options are wrong
- A. NER extracts specific entities from text, not categorizes the entire document.
- C. Sentiment Analysis determines emotional tone, not predefined document categories.
- D. Key Phrase Extraction identifies important phrases, not the overall category.
Custom Text Classification
A feature of Azure AI Language that allows users to train a custom model to classify text into user-defined categories based on labeled examples.
- Requires labeled training data.
- Ideal for domain-specific text categorization.
- Scalable for high volumes of text.
Memory trick: Classify emails with custom rules, like a meticulous librarian.