Describe features of Natural Language Processing workloads on Azure →mediumMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
A customer support team receives thousands of unstructured chat transcripts every day. They want to automatically identify the most common recurring issues (e.g., 'long wait time', 'payment error', 'login problem') without training a custom model. Which prebuilt Azure AI Language feature should they use?
⚠ Common exam trap
Watch out — candidates often confuse Named Entity Recognition (NER) with key phrase extraction, mistakenly thinking NER can extract arbitrary recurring topics when it is strictly limited to predefined entity types like person, location, or organization.
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
✓
Key phrase extraction
Key phrase extraction is the correct choice because it automatically identifies the most salient topics or 'key phrases' from unstructured text without requiring any custom training. In this scenario, the recurring issues like 'long wait time' or 'payment error' are exactly the type of multi-word, topic-level phrases that key phrase extraction surfaces, making it the ideal prebuilt feature for summarizing common support topics.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Key phrase extraction
Why this is correct
Key phrase extraction scans unstructured chat and returns the most salient words and phrases using statistical weighting, without needing a predefined category set. By aggregating these extracted phrases across thousands of conversations, the team can rank recurring topics such as 'password reset' or 'refund delay.' This makes it the correct choice for surfacing common issues from chat transcripts.
- ✗
Named entity recognition (NER)
Why it's wrong here
Named entity recognition (NER) labels text spans with predefined semantic categories such as PERSON, ORGANIZATION, LOCATION, DATE, and QUANTITY, rather than identifying open-ended themes. In a customer support transcript, NER might extract a product name or a date of contact, but it cannot detect a recurring problem like 'checkout error' because that phrase is not a recognized entity type. Therefore NER fails to surface common issues.
When this WOULD be correct
NER would be correct if the question asked to automatically extract specific named entities such as product names, company names, or locations from customer support chats, without needing to identify general recurring issues.
- ✗
Sentiment analysis
Why it's wrong here
Sentiment analysis evaluates each chat message or transcript as positive, negative, neutral, or mixed, and can return confidence scores for those labels. While it might reveal that customers are frustrated, it does not state the specific reason for that frustration, such as a bug or a missing order. Thus sentiment analysis measures emotion rather than extracting the concrete issues the support team needs.
When this WOULD be correct
A company wants to automatically gauge customer satisfaction from chat transcripts by detecting whether each conversation is positive, negative, or neutral. They need a prebuilt feature that does not require custom training.
- ✗
Language detection
Why it's wrong here
Language detection only assigns a language code and confidence score to each piece of chat text, such as 'en' or 'es', based on the script and vocabulary. It gives the support team no insight into the subject matter or recurring problems mentioned in the conversations. Knowing whether a customer wrote in English or Spanish does not help identify the common issues they are facing.
When this WOULD be correct
A question like: 'A multinational company receives customer feedback in multiple languages and needs to route each message to the appropriate language-specific support team. Which prebuilt Azure AI Language feature should they use?'
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.
✓Key phrase extractionCorrect answer▾
Why this is correct
Key phrase extraction scans unstructured chat and returns the most salient words and phrases using statistical weighting, without needing a predefined category set. By aggregating these extracted phrases across thousands of conversations, the team can rank recurring topics such as 'password reset' or 'refund delay.' This makes it the correct choice for surfacing common issues from chat transcripts.
✗Named entity recognition (NER)Wrong answer — click to see why▾
Why this is wrong here
Named entity recognition (NER) identifies specific entities like people, places, or organizations, not general recurring issues from unstructured chat transcripts. The goal is to extract common themes like 'payment error', which requires key phrase extraction.
★ When this WOULD be the correct answer
NER would be correct if the question asked to automatically extract specific named entities such as product names, company names, or locations from customer support chats, without needing to identify general recurring issues.
Why candidates choose this
Candidates may confuse NER with key phrase extraction because both involve extracting information from text, but NER focuses on predefined categories of entities rather than open-ended key phrases representing issues.
✗Sentiment analysisWrong answer — click to see why▾
Why this is wrong here
Sentiment analysis determines the emotional tone (positive, negative, neutral) of text, but does not extract specific topics or issues like 'long wait time' or 'payment error'. The goal is to identify recurring issues, not sentiment.
★ When this WOULD be the correct answer
A company wants to automatically gauge customer satisfaction from chat transcripts by detecting whether each conversation is positive, negative, or neutral. They need a prebuilt feature that does not require custom training.
Why candidates choose this
Candidates may confuse 'identifying issues' with 'identifying sentiment', thinking that negative sentiment correlates with issues, but sentiment analysis does not extract the specific issue itself.
✗Language detectionWrong answer — click to see why▾
Why this is wrong here
Language detection identifies the language of text (e.g., English, Spanish), not the topics or issues within chat transcripts. The goal is to find recurring issues like 'long wait time', which requires extracting key phrases, not detecting language.
★ When this WOULD be the correct answer
A question like: 'A multinational company receives customer feedback in multiple languages and needs to route each message to the appropriate language-specific support team. Which prebuilt Azure AI Language feature should they use?'
Why candidates choose this
Candidates may confuse language detection with text analysis, thinking that identifying the language is a necessary first step before analyzing content, but the question specifically asks for identifying issues, not languages.
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
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.
Key term
Feature
A feature is a distinct unit of functionality that delivers value to the user, often managed and tracked throughout the software development lifecycle.
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.