AI-102 Practice Question: Implement knowledge mining and information extraction solutions
A company uses Azure AI Search to index customer support transcripts. They want to enable users to find relevant answers by asking natural language questions. Which feature should they enable in the search service?
⚠ Common exam trap
AI-102 often tests the distinction between semantic search and other Azure AI Search features — candidates may confuse semantic search with synonym maps or cognitive skills, which serve different purposes.
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
✓
Semantic search
Semantic search in Azure AI Search enhances the ranking of results by using language understanding models to re-rank matches based on semantic relevance to the query, enabling users to ask natural language questions and get more relevant answers. It is the feature designed to improve relevance for natural language queries.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Semantic search
Why this is correct
Semantic search adds a reranking layer over results using Microsoft's language models, matching natural-language questions to the most relevant passages in the transcripts. This directly satisfies the stem's requirement to find answers by asking questions, since keyword search alone cannot interpret query intent or rank by semantic relevance.
- ✗
Synonym maps
Why it's wrong here
Synonym maps only expand query terms to equivalent words; they cannot interpret natural-language questions or rank passages by semantic relevance. They are tempting because they genuinely improve recall for domain jargon and product aliases, and would be the right choice when users search with known abbreviations rather than full questions.
- ✗
Cognitive skills
Why it's wrong here
Cognitive skills enrich indexed content during ingestion, such as extracting entities or key phrases, but do not interpret natural language questions or return answers. It tempts because skills feed the semantic ranking pipeline, and would be correct when the requirement is enriching documents rather than enabling question answering.
- ✗
Knowledge mining
Why it's wrong here
Knowledge mining is an overall solution pattern for extracting insights from large document sets, not a search feature that answers natural language questions. It tempts because it is built on Azure AI Search and cognitive skills, and would be correct when the goal is discovering structured information across unstructured 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 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.