Azure Language PII Detection for Data Masking

AI-901 By islever Editorial Last updated Oct 15, 2026

Implement AI solutions for text and speech by using Foundry

Short answer

A Use Personally Identifiable Information (PII) detection to automatically identify and mask sensitive data like names and phone numbers in text.

Question

Which feature of the Azure Language in Foundry Tools service should you use to automate the masking of names and phone numbers in text data?

Personally Identifiable Information (PII) detection Correct Answer
custom text classification
entity linking
custom named entity recognition (NER)

Key Takeaways

The question tests knowledge of Azure AI Language features, with the common trap being confusion between custom NER and built-in PII detection for standard sensitive data types.

This question tests the capability of Azure AI Language's Personally Identifiable Information (PII) detection feature to automatically identify and mask sensitive data like names and phone numbers. It establishes that built-in PII detection is the standard tool for this automation task.

Common mistake: Learners often choose Custom Named Entity Recognition (NER) because it sounds more technical, but they fail to recognize that PII detection is a pre-built, optimized solution specifically for masking sensitive information without training overhead.

Expert Analysis

Why the Answer Is Correct

Personally Identifiable Information (PII) detection in Azure AI Language is explicitly designed to detect and redact sensitive information from text. This includes entities such as names, phone numbers, email addresses, and credit card numbers. The service provides pre-built models that can automatically mask this data, making it the ideal choice for automating the masking of names and phone numbers.

Why the Other Options Are Wrong

Custom text classification is used to categorize documents into predefined classes, not to extract or mask specific entities. Entity linking connects extracted entities to known knowledge base entries, which does not address the need for masking. Custom named entity recognition (NER) allows you to train models to find custom entities, but it requires significant effort to build and maintain, whereas PII detection is a ready-to-use service specifically tailored for common sensitive data types.

Community Comment Notes

Community consensus strongly supports option A. One user noted that PII detection is "specifically designed to: Detect sensitive information... Redact or mask the detected information automatically." Another user confirmed this by referencing the official Microsoft documentation on PII overview, reinforcing that this is the correct feature for the task.

Official Reference

https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/overview

This link opens the official vendor documentation in a new tab.

Exam Strategy

When asked about detecting or masking sensitive data like names, emails, or financial info, immediately consider PII detection before custom solutions. Remember that built-in services are preferred for standard patterns unless unique, non-standard entities are involved.

Frequently Asked Questions

Why not use Custom NER for masking names?

Custom NER requires training and maintenance. PII detection is a pre-built, optimized service specifically for common sensitive data types like names and phones.

Does PII detection support phone number masking?

Yes, Azure AI Language PII detection includes built-in models that recognize and can redact phone numbers along with other personal identifiers.

More AI-901 FAQ →

Discussion 2 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 2

BabiRahul 👍 1 Answered A

Correct Answer: A. Personally Identifiable Information (PII) detection Why? PII Detection in Azure AI Language (Foundry Tools) is specifically designed to: Detect sensitive information such as names, phone numbers, email addresses, credit card numbers, and other personal data. Redact or mask the detected information automatically. Why the others are incorrect: B. Custom text classification → Categorizes text into predefined classes; it does not identify and mask personal data. C. Entity linking → Connects recognized entities to a knowledge base (for example, linking "Microsoft" to the Microsoft organization). D. Custom Named Entity Recognition (NER) → Identifies custom entities but does not provide built-in PII detection and redaction capabilities.
8ae956d 👍 1 Answered A

I belive that PII is the correct answer: https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/overview

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Practice All AI-901 Questions

Access 105 questions with complete answers and detailed explanations.

View Full AI-901 Practice Test →

← Back to AI-901 Study Guide