Courseiva

AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure

What is 'key phrase extraction' in Azure AI Language?

⚠ Common exam trap

Watch out — candidates often confuse key phrase extraction with entity recognition or extractive question answering, as all three involve extracting text but serve fundamentally different purposes—key phrases summarize topics, entities identify specific named items, and QA retrieves direct answers to questions.

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

Identifying the most important words and phrases that best represent a text's main topics

Key phrase extraction in Azure AI Language uses natural language processing to identify the most salient words and phrases that summarize the main topics of a text. It analyzes the document's structure and semantics to return a ranked list of key phrases, enabling quick understanding of core content without reading the entire text.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Encrypting sensitive phrases in a document for secure storage

    Why it's wrong here

    Encrypting sensitive phrases in a document is a data-protection operation, not a text-analysis operation. Azure AI Language key phrase extraction performs natural language understanding to find semantically salient terms, whereas encryption transforms data using cryptographic algorithms to prevent unauthorized access. The purpose is security, not topic discovery, so this does not match key phrase extraction.

  • Identifying the most important words and phrases that best represent a text's main topics

    Why this is correct

    Key phrase extraction is an Azure AI Language feature that uses natural language processing to identify the most significant words and phrases in a text, essentially capturing the central themes. It evaluates the semantic weight and contextual importance of terms rather than merely counting word frequency. This output supports downstream tasks like document tagging, summarization, and search indexing, making it the correct definition.

  • Finding and extracting password-like phrases from user messages for security monitoring

    Why it's wrong here

    Detecting password-like strings in messages is a credential-scanning or data-loss-prevention task, not key phrase extraction. Key phrase extraction has no concept of secrets or security policy; it returns topically important terms such as 'customer satisfaction' or 'quarterly revenue' from general text. Identifying credentials typically requires pattern matching, entropy checks, or specialized security models.

  • Selecting the highest-scoring responses from a list of candidate answers

    Why it's wrong here

    Selecting the highest-scoring answer from a list of candidates is the role of a question-answering system, such as Azure AI Language's extractive or conversational QA. Key phrase extraction does not compare or rank alternatives; it simply analyzes a single text and outputs the salient phrases that represent its key ideas. Therefore, this describes answer selection, not key phrase extraction.

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 →

How Courseiva writes practice questions · Editorial policy

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.