Describe features of Natural Language Processing workloads on Azure →hardMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
A healthcare organization needs to automatically redact personally identifiable information (PII) such as patient names and addresses from unstructured medical notes, while keeping clinical terms like disease names and medications. They want to use prebuilt Azure AI Language features without any custom training. Which combination of features should they use?
⚠ Common exam trap
A common mix-up: candidates confuse general-purpose Named Entity Recognition (NER) with the specialized Text Analytics for Health feature, or assume that PII detection alone can handle clinical terms, when in fact two separate prebuilt features are needed for this specific healthcare redaction task.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
PII detection and Text Analytics for Health
PII detection identifies and redacts personally identifiable information like patient names and addresses, while Text Analytics for Health extracts clinical entities such as diseases and medications from unstructured medical notes. Both are prebuilt Azure AI Language features that require no custom training, making them ideal for this healthcare redaction scenario.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
PII detection and Text Analytics for Health
Why this is correct
PII detection identifies personal information such as names, dates, and identification numbers in clinical notes, while Text Analytics for Health extracts medical entities like diagnoses, medications, and symptoms. Both are prebuilt Azure Cognitive Service features that require no custom training, and their correlation makes it possible to redact sensitive data while preserving the clinical context needed for care.
- ✗
Key phrase extraction and sentiment analysis
Why it's wrong here
Key phrase extraction surfaces the most important terms in a document irrespective of whether they are clinical or personal, meaning it would not isolate sensitive identifiers for redaction. Sentiment analysis assigns a positive, negative, or neutral tone score, which is unrelated to privacy and would not help identify personal data or medical concepts. Neither feature offers any masking, deletion, or redaction capability, making this pair entirely unsuitable for the task.
When this WOULD be correct
A company wants to analyze customer feedback to identify common topics and overall sentiment trends without needing to redact any information.
- ✗
Named Entity Recognition (NER) and language detection
Why it's wrong here
The standard prebuilt NER in Azure recognizes generic categories such as person, organization, and location, but it lacks medical-specific entity types like drug names, clinical conditions, or ICD-10 codes, so it cannot fully understand healthcare text. Language detection merely identifies the language of the document and provides no redaction or personal-data masking capability. This combination therefore fails to meet the clinical and privacy requirements of the scenario.
When this WOULD be correct
An exam scenario where the task is to extract all named entities (e.g., persons, locations, organizations) from multilingual documents and identify the language of each document, without any redaction or clinical analysis. For example: 'A global news agency needs to extract entity names from articles in multiple languages and detect the language of each article.'
- ✗
Entity linking and conversational language understanding
Why it's wrong here
Entity linking disambiguates text by mapping mentions to knowledge-base identifiers (like Wikipedia or UMLS concepts), which is useful for semantically enriching content but does not mask or remove personal data. Conversational language understanding is designed for intent and entity extraction in chatbot dialogues, not for analyzing unstructured clinical notes. Together, they address neither the redaction requirement nor the specialized medical extraction need.
When this WOULD be correct
A question asks: 'Which Azure AI Language features should be used to identify and link medical terms to a standardized ontology (e.g., ICD-10) in clinical notes?' Then entity linking would be correct, possibly combined with Text Analytics for Health.
Option-by-option analysis
Why each answer is right or wrong
Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.
✓PII detection and Text Analytics for HealthCorrect answer▾
Why this is correct
PII detection identifies personal information such as names, dates, and identification numbers in clinical notes, while Text Analytics for Health extracts medical entities like diagnoses, medications, and symptoms. Both are prebuilt Azure Cognitive Service features that require no custom training, and their correlation makes it possible to redact sensitive data while preserving the clinical context needed for care.
✗Key phrase extraction and sentiment analysisWrong answer — click to see why▾
Why this is wrong here
Key phrase extraction and sentiment analysis do not detect or redact PII; they analyze topics and emotions, not sensitive data like names or addresses.
★ When this WOULD be the correct answer
A company wants to analyze customer feedback to identify common topics and overall sentiment trends without needing to redact any information.
Why candidates choose this
Candidates may confuse key phrase extraction with entity recognition, assuming it can identify names, or think sentiment analysis helps detect sensitive content.
✗Named Entity Recognition (NER) and language detectionWrong answer — click to see why▾
Why this is wrong here
Named Entity Recognition (NER) identifies entities like names and diseases but does not redact PII, and language detection only identifies the language, not redact or analyze clinical content. The question requires redaction of PII and analysis of clinical terms, which NER and language detection cannot fulfill together.
★ When this WOULD be the correct answer
An exam scenario where the task is to extract all named entities (e.g., persons, locations, organizations) from multilingual documents and identify the language of each document, without any redaction or clinical analysis. For example: 'A global news agency needs to extract entity names from articles in multiple languages and detect the language of each article.'
Why candidates choose this
Candidates may confuse NER with PII detection, thinking NER can redact PII, and assume language detection is needed for multilingual medical notes, overlooking that the question specifies redaction and clinical analysis.
✗Entity linking and conversational language understandingWrong answer — click to see why▾
Why this is wrong here
Entity linking maps named entities to a knowledge base (e.g., Wikipedia), not for redacting PII. Conversational language understanding (CLU) is for intent classification in chatbots, not for processing unstructured medical notes for redaction.
★ When this WOULD be the correct answer
A question asks: 'Which Azure AI Language features should be used to identify and link medical terms to a standardized ontology (e.g., ICD-10) in clinical notes?' Then entity linking would be correct, possibly combined with Text Analytics for Health.
Why candidates choose this
Candidates may think 'entity linking' sounds similar to 'named entity recognition' (which is part of PII detection) and assume CLU can handle any language understanding task, including redaction.
Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Text analytics
Text analytics is the process of turning unstructured text, like emails or social media posts, into structured data that can be analyzed to find patterns, sentiments, and insights.
Key term
Azure AI Language
Azure AI Language is a cloud-based service from Microsoft that uses natural language processing to understand, analyze, and generate human language for applications.
About these practice questions
This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.