Courseiva

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

A legal firm needs to process thousands of contracts to automatically identify important terms such as dates, monetary amounts, names of parties, and legal citations. Which built-in feature of the Azure AI Language service is best suited for this task?

⚠ Common exam trap

Candidates often confuse Key Phrase Extraction with Entity Recognition, assuming both extract 'important terms' — but Key Phrase Extraction lacks the predefined, structured categorization needed for specific data types like dates and monetary amounts.

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

C) Entity Recognition

Entity Recognition (also called Named Entity Recognition, NER) is the correct choice because it is specifically designed to identify and categorize predefined entities such as dates, monetary amounts, person names, organizations, and legal citations from unstructured text. The Azure AI Language service's NER capability can automatically extract these important terms from thousands of contracts, making it the ideal built-in feature for this task.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • A) Sentiment Analysis

    Why it's wrong here

    Sentiment analysis returns a sentiment label and confidence scores for positive, negative, and neutral text, but it does not isolate individual facts such as contract parties, effective dates, or dollar amounts. For a legal contract workflow, the goal is structured data extraction, not opinion mining, so sentiment analysis would fail to produce the specific fields required. To extract those values, you need named entity recognition instead.

  • B) Key Phrase Extraction

    Why it's wrong here

    Key Phrase Extraction surfaces the most salient topics or talking points in a document, but it returns unlabeled strings rather than categorizing them as recognizable entity types. While the phrase 'net 30 days' might appear as a key phrase, the service does not tag it as a duration or payment term, so downstream systems cannot reliably populate a contract database. Entity recognition, in contrast, labels each token with a semantic type.

  • C) Entity Recognition

    Why this is correct

    Entity Recognition, specifically Azure AI Language's Named Entity Recognition (NER), identifies and categorizes entities in text into predefined types such as Date, Currency/Amount, Person, Organization, and Address. In a contract, it can extract the effective date as a DATE entity, the contract value as a Money entity, and the involved firms as Organization entities, making it the correct service. This enables automated downstream processing without manual review.

  • D) Language Detection

    Why it's wrong here

    Language Detection identifies the dominant language of a document and returns a language code and score, but it provides no insight into the semantic content, parties, or financial terms. A contract written in English would simply be labeled 'en', which is irrelevant if the task is to pull out dates or monetary values. It is a preprocessing step, not an information extraction tool.

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 →

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.