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 law firm receives hundreds of legal documents daily. They need to automatically extract key entities like names of parties, dates, jurisdictions, and also classify each document as 'contract', 'pleading', or 'memo'. Which combination of Azure AI Language features should they use?
⚠ Common exam trap
Many exam-takers confuse key phrase extraction with entity recognition, assuming key phrases can replace entities, but key phrases are unstructured and not mapped to predefined categories like dates or jurisdictions.
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
✓
Entity recognition and custom text classification
The law firm needs both entity extraction (to identify parties, dates, jurisdictions) and document classification (contract, pleading, memo). Azure AI Language's prebuilt entity recognition handles the entity extraction, while custom text classification allows the firm to train a model to classify documents into their specific categories. This combination directly addresses both requirements without unnecessary features.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Entity recognition and key phrase extraction
Why it's wrong here
Entity recognition in Azure AI Language extracts prebuilt named entities such as people, organizations, dates, and locations, while key phrase extraction returns the most salient words or phrases in a document. Neither capability assigns a legal document to a user-defined category, so this combination cannot classify hundreds of legal documents into types like contracts or subpoenas. You need custom text classification for that label assignment.
- ✓
Entity recognition and custom text classification
Why this is correct
Custom text classification trains a model on labeled examples to assign each legal document to a predefined type such as contract, summons, or memorandum, while entity recognition extracts structured metadata like party names, dates, and amounts. Together they accomplish the two stated needs: sorting documents into the required legal categories and pulling out key entities for downstream processing. This matches the law firm's document intake pipeline directly.
- ✗
Sentiment analysis and language detection
Why it's wrong here
Sentiment analysis scores text on a positive, negative, or neutral continuum, and language detection identifies the dominant language, usually for multilingual or opinion-oriented workloads. These outputs do not extract legal entities like contract parties or filing dates, nor do they classify documents into practice-area categories, so they cannot support the firm's need to organize incoming legal papers. They answer "how people feel" or "what language is used," not "what kind of document is this."
- ✗
Summarization and conversation analysis
Why it's wrong here
Document summarization condenses the source text into a shorter abstractive or extractive summary, which might help a human skim a document but does not assign a document type. Conversation analysis, including conversational language understanding, is designed for dialogue, chat logs, or meeting transcripts, not for static legal documents, and it likewise does not perform entity extraction for parties or dates. This combination would produce summaries and handle conversations, but it fails on both required tasks: classification and legal entity extraction.
Go deeper
Related to this question
Learn chapter
Regression and Classification
Key term
Entity extraction
Entity extraction is the process of automatically identifying and classifying named entities in text, such as people, organizations, locations, dates, and technical terms, turning unstructured data into structured information.
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
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.