Courseiva

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

A customer support team wants to use Azure AI Language to automatically analyze incoming support emails. They need to extract the product name mentioned in each email and determine whether the customer's sentiment is positive, negative, or neutral. They have no labeled data for custom training. Which two prebuilt Azure AI Language features should they use together?

⚠ Common exam trap

Microsoft often tests the distinction between prebuilt features (NER, sentiment analysis) that require no training data versus custom features (CLU) that need labeled data, causing candidates to mistakenly choose CLU for entity extraction without realizing it requires custom training.

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

Named entity recognition (NER) and sentiment analysis

Named entity recognition (NER) extracts specific entities like product names from text, while sentiment analysis determines the emotional tone (positive, negative, neutral). Both are prebuilt, no-code features in Azure AI Language that require no labeled data for custom training, making them the correct pair for this use case.

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 and language detection

    Why it's wrong here

    Key phrase extraction returns the most relevant words and phrases in a document, but these are untyped text spans, so they may be partial or imprecise and do not reliably identify the exact product-name entities. Language detection only determines whether the email is, for example, English or Spanish, which has no bearing on product names or sentiment. Thus this combination fails to provide the structured entity extraction and opinion classification needed.

    When this WOULD be correct

    A scenario where the team needs to identify the language of incoming emails and extract key terms (like product names) without needing sentiment analysis. For example, routing emails to language-specific queues and extracting main topics.

  • Named entity recognition (NER) and sentiment analysis

    Why this is correct

    Named entity recognition (NER) in Azure AI Language identifies product names through its prebuilt Product entity category, so no custom model is required to pull product names from emails. Sentiment analysis separately classifies each email's tone as positive, negative, neutral, or mixed by scoring the text. Together these two prebuilt capabilities directly satisfy the requirement to extract product names and determine sentiment, and they can be called through the same Language service endpoint.

  • Conversational language understanding (CLU) and translation

    Why it's wrong here

    Conversational language understanding (CLU) is a custom feature that requires labeled training data and model deployment, making it unnecessarily complex compared with prebuilt NER for this task. Translation converts text between languages and preserves content, but it neither extracts product names nor classifies sentiment. As a result, this option adds custom effort while still not delivering the required outputs.

    When this WOULD be correct

    A customer support chatbot needs to understand user intents (e.g., 'reset password') and extract entities from chat messages, then translate responses for a multilingual audience. In that scenario, CLU and translation would be the correct pair.

  • Text summarization and personal identifying information (PII) detection

    Why it's wrong here

    Text summarization produces a concise version of an email but does not structurally return entities such as product names, nor does it assign a sentiment label. PII detection locates sensitive data like credit card numbers, social security numbers, or phone numbers, which is useful for redaction but irrelevant to product extraction or tone. Because neither capability maps to the two required outputs, this pairing is incorrect.

    When this WOULD be correct

    A question requiring removal of sensitive information from documents before sharing, such as 'A legal team needs to redact personal data from contracts and generate concise summaries for review.' Then text summarization and PII detection would be correct.

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.

Named entity recognition (NER) and sentiment analysisCorrect answer

Why this is correct

Named entity recognition (NER) in Azure AI Language identifies product names through its prebuilt Product entity category, so no custom model is required to pull product names from emails. Sentiment analysis separately classifies each email's tone as positive, negative, neutral, or mixed by scoring the text. Together these two prebuilt capabilities directly satisfy the requirement to extract product names and determine sentiment, and they can be called through the same Language service endpoint.

Key phrase extraction and language detectionWrong answer — click to see why

Why this is wrong here

Key phrase extraction identifies important terms but does not categorize them as product names, and language detection only identifies the language, not sentiment. The question requires extracting product names (NER) and sentiment analysis, not language detection.

★ When this WOULD be the correct answer

A scenario where the team needs to identify the language of incoming emails and extract key terms (like product names) without needing sentiment analysis. For example, routing emails to language-specific queues and extracting main topics.

Why candidates choose this

Candidates may confuse key phrase extraction with named entity recognition, thinking it can extract product names, and overlook that language detection is irrelevant to sentiment analysis.

Conversational language understanding (CLU) and translationWrong answer — click to see why

Why this is wrong here

Conversational language understanding (CLU) is designed for intent and entity extraction from conversational utterances, not for analyzing static support emails. Translation is irrelevant because the question does not mention multilingual needs.

★ When this WOULD be the correct answer

A customer support chatbot needs to understand user intents (e.g., 'reset password') and extract entities from chat messages, then translate responses for a multilingual audience. In that scenario, CLU and translation would be the correct pair.

Why candidates choose this

Candidates may think CLU can extract product names (entities) and translation might be needed for multilingual emails, but the question specifies no custom training and focuses on prebuilt features for email analysis.

Text summarization and personal identifying information (PII) detectionWrong answer — click to see why

Why this is wrong here

Text summarization condenses content but does not extract product names, and PII detection identifies personal data like names or addresses, not product names or sentiment. Neither feature meets the requirements of extracting product names or analyzing sentiment.

★ When this WOULD be the correct answer

A question requiring removal of sensitive information from documents before sharing, such as 'A legal team needs to redact personal data from contracts and generate concise summaries for review.' Then text summarization and PII detection would be correct.

Why candidates choose this

Candidates may think 'summarization' can extract key details like product names, and 'PII detection' seems related to analyzing email content, but they confuse data extraction with content analysis.

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

About these practice questions

Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.