Describe features of Natural Language Processing workloads on Azure →hardMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
A law firm needs to automatically categorize documents (e.g., 'contract', 'pleading', 'memo') and extract specific clauses such as 'indemnity' and 'confidentiality'. They have a large set of labeled examples for both tasks. Which combination of Azure AI Language features should they use?
⚠ Common exam trap
Many candidates confuse prebuilt features (like sentiment analysis or key phrase extraction) with custom features, assuming that prebuilt models can be adapted to domain-specific tasks without training, when in fact only custom text classification and custom NER can leverage labeled examples for tailored document categorization and entity extraction.
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 and custom named entity recognition
The law firm needs to categorize documents (a text classification task) and extract specific clauses (a named entity recognition task). Custom text classification allows training a model on labeled examples to classify documents into categories like 'contract' or 'pleading', while custom named entity recognition (NER) can be trained to extract domain-specific entities such as 'indemnity' and 'confidentiality' clauses from the text. Azure AI Language supports both custom features, enabling the firm to build tailored models using their labeled dataset.
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 sentiment analysis and key phrase extraction
Why it's wrong here
Prebuilt sentiment analysis and key phrase extraction are generic Azure AI Language features. Sentiment analysis only assigns a positivity/negativity/neutrality score per sentence or document, while key phrase extraction returns a statistical list of salient phrases such as 'contract' or 'client' without any legal-domain training. These tools cannot be trained on a firm's custom taxonomy, so they cannot categorize documents into law-firm-specific classes like 'non-disclosure agreement' nor extract custom entities like 'indemnification clause.' Because the requirement is for custom categories and custom named entities, these prebuilt generic NLP functions are insufficient.
- ✓
Custom text classification and custom named entity recognition
Why this is correct
Custom text classification and custom named entity recognition (NER) are the correct Azure AI Language capabilities. Custom text classification lets you train a model on labeled documents to assign them to your own legal categories (e.g., 'NDA', 'employment contract', 'litigation hold'), while custom NER trains a model to extract user-defined entity types such as contract effective dates, governing law clauses, or named parties. Both require a labeled training dataset and produce a custom endpoint that infers structured labels and entities from new documents. This directly matches the law firm's need to automatically categorize documents and pull specific clause-level information, unlike any generic prebuilt service.
- ✗
Question answering and conversation summarization
Why it's wrong here
Question answering and conversation summarization are designed for different workloads. Azure AI Language question answering returns answer spans from a knowledge base or a document set in response to queries, but it does not assign each document a predefined category label. Conversation summarization (extractive or abstractive) condenses a conversation transcript into key points or a summary; it neither classifies documents into custom legal types nor extracts structured named entities like specific clause identifiers. These tools are meant for interactive Q&A or summarizing chat/meetings, not for batch document categorization in a legal practice.
- ✗
Language detection and translation
Why it's wrong here
Language detection and translation address surface-level linguistic properties, not semantics or domain-specific structure. Language detection uses a prebuilt classifier to identify the dominant language of text (e.g., English vs. Spanish), while Azure Translator converts text between languages using statistical or neural machine translation. Neither feature can be trained on the law firm's own categories, and they produce no structured classification of documents or extraction of legal entities. Because the task requires categorizing documents into firm-specific types and extracting custom named entities, these language-level operations are irrelevant and cannot accomplish the goal.
Go deeper
Related to this question
Learn chapter
Regression and Classification
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
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
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.