AI-102 Practice Question: Implement natural language processing solutions
You are designing an NLP solution to analyze legal documents. The solution must identify specific clauses and parties involved. Which Azure AI service is most appropriate?
⚠ Common exam trap
Many candidates confuse Pre-built NER with Custom NER, assuming the pre-built model can handle domain-specific entities like legal clauses, but it only recognizes generic categories and cannot be retrained.
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 Named Entity Recognition in Azure AI Language
Custom Named Entity Extraction (Custom NER) in Azure AI Language is the correct choice because it allows you to train a model to recognize domain-specific entities like legal clauses and party names from your own labeled data. Pre-built NER only recognizes generic entity types (e.g., person, organization, location) and cannot be customized for legal terminology. This makes Custom NER the only option that meets the requirement to identify specific clauses and parties unique to legal documents.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Custom Named Entity Recognition in Azure AI Language
Why this is correct
Custom Named Entity Recognition trains a model on your labelled legal data to extract domain-specific entities such as clauses and party names, which prebuilt models cannot recognise. It satisfies the requirement to identify bespoke fields rather than generic persons or organisations.
- ✗
Pre-built Named Entity Recognition in Azure AI Language
Why it's wrong here
Pre-built NER recognises general entities such as people, organisations and locations, but not bespoke legal clause types or party roles defined by contract language. It would be correct for extracting standard entities from unstructured text without domain-specific training or custom labels.
- ✗
Text Analytics for Health
Why it's wrong here
Text Analytics for Health extracts medical entities, medications and clinical relations from clinical text, so it cannot identify contract clauses or party roles. It would be the right service for parsing patient records, discharge summaries or clinical trial notes into structured medical data.
- ✗
Immersive Reader
Why it's wrong here
Immersive Reader is an accessibility reading aid that adjusts text presentation and read-aloud output; it performs no entity or clause extraction. It would be the right choice when the requirement is improving comprehension for readers with dyslexia or visual impairment, not analysing document content.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 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-102 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-102 exam.