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 legal firm needs to automatically extract specific terms such as contract dates, party names, and monetary amounts from thousands of legal documents. The firm does not have a labeled dataset for custom training but needs to identify only these predefined types of information. Which prebuilt Azure AI Language feature should they use?
⚠ Common exam trap
Test-takers frequently confuse key phrase extraction with named entity recognition, thinking that extracting 'key terms' is equivalent to identifying specific entity types, but key phrase extraction returns general phrases (e.g., 'the contract date') rather than structured entity values (e.g., 'January 15, 2024').
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)
Named Entity Recognition (NER) is the correct choice because it is a prebuilt Azure AI Language feature designed to automatically identify and categorize predefined entities such as dates, person names, and monetary amounts from text. Since the firm needs to extract specific types of information (contract dates, party names, monetary amounts) without a labeled dataset, NER's out-of-the-box models can directly recognize these common entity categories without any custom training.
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 it's wrong here
Key phrase extraction returns an unordered, ranked list of salient phrases based on statistical relevance, such as 'breach of contract' or 'dispute resolution', but it does not assign each phrase to a semantic category. Because it highlights important topics rather than every mention of a predefined type, it will not reliably capture all monetary amounts or dates, and it does not normalize or structure them for downstream processing. It is a topic-summarization technique, not a schema-bound extraction capability.
When this WOULD be correct
A company wants to automatically extract the most important topics or keywords from customer feedback without needing to classify them into predefined categories. Key phrase extraction would be the correct choice.
- ✓
Named Entity Recognition (NER)
Why this is correct
Named Entity Recognition (NER) is purpose-built for locating and classifying span-level mentions from unstructured legal text, extracting typed entities such as persons, organizations, dates, and monetary amounts. In Azure AI Language's pretrained NER model, each extracted term is returned with a category, subcategory, and confidence score, which satisfies the requirement of pulling out specific contractual terms without custom annotation. Because it directly maps text spans to fixed semantic types, it is the correct service.
- ✗
Sentiment analysis
Why it's wrong here
Sentiment analysis evaluates the attitude expressed in a document or sentence, returning a positive/negative/neutral/mixed label and associated confidence scores, not a set of extracted data points. A sentence such as 'The lessee shall pay USD 5,000 on January 15' has no clear sentiment yet contains exactly the kind of terms the firm needs. The service is designed to gauge opinion and emotion, not to locate or type individual mentions like dates or amounts.
When this WOULD be correct
A company wants to automatically gauge customer satisfaction from product reviews by identifying whether the feedback is positive, negative, or neutral. Sentiment analysis would be the correct prebuilt feature.
- ✗
Language detection
Why it's wrong here
Language detection identifies which language a document is written in by analyzing character sets and lexical patterns, then returning a language code such as 'en' or 'es', not the substantive terms within the text. It operates at the whole-document level and is often used as a routing step before other analysis, so it cannot produce individual mentions like 'January 15, 2026' or '$500,000'. For a legal firm, knowing that a contract is in English tells them nothing about the specific clauses or data encoded in it.
When this WOULD be correct
A multinational company receives documents in multiple languages and needs to automatically route them to the appropriate language-specific processing pipeline. Language detection would be the correct feature to identify each document's language.
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)Correct answer▾
Why this is correct
Named Entity Recognition (NER) is purpose-built for locating and classifying span-level mentions from unstructured legal text, extracting typed entities such as persons, organizations, dates, and monetary amounts. In Azure AI Language's pretrained NER model, each extracted term is returned with a category, subcategory, and confidence score, which satisfies the requirement of pulling out specific contractual terms without custom annotation. Because it directly maps text spans to fixed semantic types, it is the correct service.
✗Key phrase extractionWrong answer — click to see why▾
Why this is wrong here
Key phrase extraction identifies general phrases (e.g., 'contract date') but does not classify them into predefined categories like dates, party names, or monetary amounts. The question requires extracting specific entity types, which is the function of NER.
★ When this WOULD be the correct answer
A company wants to automatically extract the most important topics or keywords from customer feedback without needing to classify them into predefined categories. Key phrase extraction would be the correct choice.
Why candidates choose this
Candidates may confuse 'extracting terms' with 'extracting key phrases,' not realizing that NER is specifically designed to identify and classify predefined entity types like dates and names.
✗Sentiment analysisWrong answer — click to see why▾
Why this is wrong here
Sentiment analysis determines the emotional tone (positive, negative, neutral) of text, not the extraction of specific entities like dates, names, or monetary amounts.
★ When this WOULD be the correct answer
A company wants to automatically gauge customer satisfaction from product reviews by identifying whether the feedback is positive, negative, or neutral. Sentiment analysis would be the correct prebuilt feature.
Why candidates choose this
Candidates may confuse 'extracting terms' with 'analyzing text' and think sentiment analysis can identify specific information, not realizing it only assesses overall sentiment.
✗Language detectionWrong answer — click to see why▾
Why this is wrong here
Language detection identifies the language of text (e.g., English, Spanish), not specific terms like contract dates or party names. The firm needs to extract predefined information, not detect the document's language.
★ When this WOULD be the correct answer
A multinational company receives documents in multiple languages and needs to automatically route them to the appropriate language-specific processing pipeline. Language detection would be the correct feature to identify each document's language.
Why candidates choose this
Candidates may confuse 'language' with 'information extraction' or think that language detection is a prerequisite step before applying other features, but the question specifically asks for extracting terms, not identifying language.
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
Types of AI Workloads
Key term
Named entity recognition
Named entity recognition (NER) is an Azure AI service feature that automatically identifies and classifies key pieces of information in text, such as names of people, organizations, locations, dates, and other specific data.
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
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 →
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.