Describe features of Natural Language Processing workloads on Azure →easyMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
A customer support team uses an AI chatbot to analyze incoming messages. They want to automatically identify the most frequently mentioned topics, such as 'shipping delay', 'refund policy', and 'product quality', without manually reading each message. Which Azure AI Language feature should they use?
⚠ Common exam trap
Candidates often confuse Entity Recognition with Key Phrase Extraction, but Entity Recognition only extracts predefined categories (e.g., person, location) and misses abstract topics like 'shipping delay' that are not named entities.
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 main topics and concepts in text, such as 'shipping delay', 'refund policy', and 'product quality', without requiring manual reading. This feature returns a list of key phrases that represent the most salient points in the input, making it ideal for topic frequency analysis in customer support messages.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Language Detection
Why it's wrong here
Language Detection identifies the dominant language of the input text and returns a language name, ISO 639-1 code, and a confidence score. It does not surface what the message is about, so in this chatbot scenario it would reveal that a ticket is in English but not that it relates to refunds or delivery delays. Topic-level insight therefore requires key phrase extraction rather than language detection.
- ✓
Key Phrase Extraction
Why this is correct
Key Phrase Extraction uses Azure AI Language's machine learning model to retrieve a ranked list of the most salient phrases from a document, capturing the main subjects and topical themes. This maps directly to the support team's goal of identifying frequently mentioned subjects in incoming messages and enables aggregation for trend reporting. Unlike entity recognition, it is not limited to predefined categories, so it can surface novel or domain-specific concerns.
- ✗
Sentiment Analysis
Why it's wrong here
Sentiment Analysis evaluates the emotional tone of the text and returns polarity scores for positive, negative, neutral, and mixed classes, with confidence levels at the document or sentence level. It measures how strongly a customer feels about an issue, but it does not reveal which issue is being discussed. The team would learn that tickets are negative, yet still lack the topic labels needed to prioritize by subject matter.
- ✗
Entity Recognition
Why it's wrong here
Entity Recognition, also called Named Entity Recognition (NER), identifies and classifies predefined elements such as persons, organizations, locations, dates, quantities, and product names, optionally linking them to a knowledge base. In customer-support messages it could extract a customer name or a product version, but it would not group colloquial phrasing around a recurring concern. Because NER depends on fixed categories, open-ended topic discovery requires key phrase extraction.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
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.
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
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.