AI-102 Practice Question: Implement natural language processing solutions
You have a Conversational Language Understanding (CLU) project in Azure AI Language. Users frequently type utterances such as 'Book a flight from Seattle to Tokyo next Friday for two people.' The solution must extract the origin city, destination city, date, and passenger count as separate structured values so the booking system can act on them. You need to configure the project to capture these values. What should you do?
⚠ Common exam trap
The trap here is assuming intents alone can produce structured values, when only labeled entities yield the extracted fields.
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
✓
Add entities to the project and label them in the training utterances, using prebuilt entities where available.
In Conversational Language Understanding, entity extraction depends on defining entities and labeling their occurrences in training utterances. Adding entities for the four values and labeling them, using prebuilt components such as geography and number where applicable, enables the model to return those values as structured fields for the booking system.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Add more intents and assign each utterance to a single intent.
Why it's wrong here
Intents classify the overall purpose of an utterance, such as BookFlight, but they do not produce separate structured values like origin city or passenger count. Adding more intents would refine classification but would not extract the four values the booking system needs, so it does not meet the requirement.
- ✗
Enable sentiment analysis and opinion mining on the CLU project.
Why it's wrong here
Sentiment analysis and opinion mining return polarity and opinions about aspects; they do not extract booking parameters such as cities, dates, or passenger counts. Enabling them would add sentiment fields to the response but would not supply the structured values required by the booking system.
- ✓
Add entities to the project and label them in the training utterances, using prebuilt entities where available.
Why this is correct
CLU extracts entities that are defined and labeled in the training utterances. Adding entities for origin, destination, date, and passenger count and labeling their spans teaches the model to return those values as structured fields. Using prebuilt components such as geography or number where available improves accuracy without building everything from scratch.
- ✗
Increase the training data by duplicating existing utterances with slight wording changes.
Why it's wrong here
Duplicating utterances increases volume but does not define the entity types or label their spans, so the model still would not return origin, destination, date, and passenger count as separate values. Data augmentation can help generalization, but it is not the configuration step that enables structured entity extraction.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.