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 wants to automatically categorize incoming legal documents into custom categories such as 'Motion', 'Contract', 'Discovery', and 'Memorandum'. The firm has a set of manually labeled documents that can be used to train the system. Which Azure AI Language feature should they use?
⚠ Common exam trap
A common mix-up: candidates confuse pre-built features (like sentiment analysis or key phrase extraction) with custom trainable features, assuming any NLP task can be solved with a pre-built model, but Azure requires custom text classification for user-defined categories.
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
✓
Custom text classification
The law firm needs to categorize documents into custom categories using their own labeled data. Custom text classification in Azure AI Language is specifically designed for this purpose, allowing you to train a model on your own labeled documents to classify text into user-defined categories. Prebuilt Text Analytics for sentiment only detects sentiment (positive/negative/neutral), not custom categories.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Prebuilt Text Analytics for sentiment
Why it's wrong here
Prebuilt Text Analytics for sentiment returns a numeric sentiment score (positive/negative/neutral) for text, but it does not produce categorical labels. The underlying model is pre-trained by Microsoft and cannot be retrained with a law firm's domain-specific categories such as contract type or practice area. While the Azure Language service includes other prebuilt features, none of them support custom document classification without building a custom model.
- ✓
Custom text classification
Why this is correct
Custom text classification is an Azure Language feature that lets you train a model on your own labeled documents to assign them to user-defined categories. For a law firm, you would label incoming documents by metadata like practice area, document type, or client matter, and the service creates a classifier that you can deploy and call via an endpoint. It supports both single-label and multi-label classification, making it the appropriate tool for this exact scenario.
- ✗
Conversational Language Understanding
Why it's wrong here
Conversational Language Understanding (CLU) is designed for natural-language understanding in interactive dialogues, extracting intents and entities from short user utterances such as chatbot commands. It assumes a turn-based conversation and is not intended for batch categorizing whole documents that arrive asynchronously. CLU's modeling is tuned for conversational structure, not for long-form, domain-specific document classification, so it would be a poor fit for a law firm's automation workflow.
- ✗
Key phrase extraction
Why it's wrong here
Key phrase extraction returns a ranked list of salient terms and phrases from a document, but it does not assign an overall category label. Because it is a generic, unsupervised text analytic, it cannot learn from labeled examples to recognize custom classes like 'contract' or 'litigation'. You would still need a human to manually interpret the extracted phrases and map them to a category, which fails the requirement for automatic categorization.
Go deeper
Related to this question
Learn chapter
Regression and Classification
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.
Key term
Classification
Classification is a supervised machine learning technique used to predict a category or class label for new data based on patterns learned from labeled training data.
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.