AI-102 Practice Question: Implement natural language processing solutions
You are building a custom question answering solution using Azure AI Language. The knowledge base contains a large number of question-answer pairs. You need to ensure that the solution returns the most relevant answer for a user's query, even when the query contains synonyms not present in the knowledge base. What should you do?
⚠ Common exam trap
The trap here is assuming that enabling a configuration setting or adding more documents will automatically handle synonyms, when the correct approach is to explicitly add alternative questions with synonyms.
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 alternative questions for each answer that include common synonyms.
Custom question answering matches user queries to questions in the knowledge base. To handle synonyms, you can add alternative questions that include common synonyms for each answer. This improves the likelihood that a query with different wording will match the correct answer. Other options do not directly address synonym matching and may not improve relevance.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable the 'enableHierarchicalExtraction' setting in the project configuration.
Why it's wrong here
Hierarchical extraction is used for extracting multiple entities from a single query, not for synonym matching. It does not affect how questions are matched to answers. Enabling it would not address the need for synonym handling and could introduce unnecessary complexity.
- ✗
Set the 'defaultAnswer' to a response that asks the user to rephrase using known terms.
Why it's wrong here
The default answer is returned when no good match is found. Using it to ask for rephrasing is a fallback, not a solution for synonym matching. It degrades user experience and does not improve the system's ability to handle synonyms. The goal is to avoid falling back by improving matching, not to rely on the fallback.
- ✓
Add alternative questions for each answer that include common synonyms.
Why this is correct
Custom question answering uses the alternative questions to match user queries. Adding synonyms as alternative questions improves recall and ensures that queries with different wording still find the correct answer. This is a supported and straightforward way to enhance relevance without changing the underlying model.
- ✗
Increase the number of documents in the knowledge base to provide more context.
Why it's wrong here
Adding more documents does not inherently improve synonym matching; it may even dilute relevance. Custom question answering matches based on the question text, so synonyms must be explicitly represented. More documents without synonyms will not help the system understand that different words mean the same thing.
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 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.