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 process thousands of legal contracts. They want to extract specific clauses (e.g., 'confidentiality', 'indemnity') and also identify the names of parties and monetary amounts mentioned. Which Azure AI Language feature(s) should they use together to achieve both tasks?
⚠ Common exam trap
Candidates often think prebuilt NER alone can handle custom clauses, but NER only recognizes a fixed set of entity types (e.g., person, organization, money) and cannot identify domain-specific clauses without custom training.
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 named entity recognition
Custom text classification allows the law firm to train a model to identify specific clauses like 'confidentiality' and 'indemnity' by providing labeled examples. Named entity recognition (NER) can then extract predefined entities such as person names (parties) and monetary amounts from the text. Together, these two features address both custom clause detection and standard entity extraction.
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 and sentiment analysis
Why it's wrong here
Key phrase extraction surfaces salient words and phrases such as 'confidentiality clause' or 'indemnification,' but it does not classify a contract into predetermined legal categories or identify specific data fields like parties and dollar amounts. Sentiment analysis only measures whether language is positive, negative, or neutral, which is irrelevant to legal obligations. Together these prebuilt Azure AI Language features lack both the custom labels required for clause-level classification and the structured entity extraction needed for contract metadata.
- ✓
Custom text classification and named entity recognition
Why this is correct
Custom text classification lets the law firm train a model on labeled examples to assign each contract to categories such as 'NDA,' 'employment agreement,' or 'contains non-compete clause,' while named entity recognition (NER) extracts structured values like party names, dates, jurisdictions, and monetary amounts from the text. By combining custom classification with NER, the solution directly addresses both document-level sorting and field-level extraction. This is the intended pattern for automated legal contract analysis in Azure AI Language.
- ✗
Entity linking and language detection
Why it's wrong here
Entity linking matches recognized entities to entries in a knowledge base like Wikipedia or Wikidata for disambiguation, but it does not organize contracts by clause type or extract contractual amounts. Language detection simply identifies the language of a document and would not help a law firm process English-language contracts or locate obligations. The combination provides no custom text classification or domain-specific NER, so it fails the task's primary requirements.
- ✗
Summarization and conversational language understanding
Why it's wrong here
Azure AI text summarization produces an extractive or abstractive summary, but a summary does not reliably enumerate every clause type or expose all parties and monetary figures in a queryable format. Conversational language understanding (CLU) is optimized for short user utterances and intents in chatbot scenarios, not for parsing long legal contracts with complex sentence structures. Neither component can perform document-level classification into legal categories or extract the structured entities required for automated contract processing.
Go deeper
Related to this question
Learn chapter
Regression and Classification
Key term
Feature
A feature is a distinct unit of functionality that delivers value to the user, often managed and tracked throughout the software development lifecycle.
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.
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.