AI-102 Practice Question: Implement knowledge mining and information extraction solutions
Which TWO Azure AI Search features should you enable to improve the relevance of search results for a knowledge mining solution that supports natural language queries?
⚠ Common exam trap
AI-102 often tests the distinction between recall-improving features (synonyms, search mode) and relevance-ranking features (semantic ranking, scoring profiles), where candidates incorrectly select synonyms or filters for relevance improvement.
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 ranking
Semantic ranking (B) is correct because it uses Microsoft's language understanding models to re-rank the top results from the initial BM25 retrieval, promoting results that are semantically relevant to natural language queries rather than just keyword matches. Scoring profiles (D) are correct because they let you boost or demote documents based on weighted fields, functions (e.g., magnitude, freshness, distance), and parameters, directly tuning relevance for the knowledge mining scenario. Synonyms (A) only expand query terms with equivalent expressions and do not provide semantic re-ranking or weighted relevance boosting. Search mode 'all' (C) merely requires all query terms to match, which is a stricter boolean behavior that can reduce recall rather than improve relevance. Filters (E) restrict the result set by criteria such as OData expressions but do not affect ranking or relevance scoring.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Synonyms
Why it's wrong here
Synonyms expand a query term to equivalents, improving recall for known vocabulary variants, but they do not interpret natural-language phrasing or rank by semantic meaning. It tempts because synonym maps are a standard relevance feature, yet semantic ranking and scoring profiles are what handle conversational queries.
- ✓
Semantic ranking
Why this is correct
Semantic ranking applies Microsoft's language models to re-rank the initial result set, so natural language queries return contextually relevant matches rather than keyword-only hits. It satisfies the requirement to improve relevance for conversational queries in the knowledge mining solution.
- ✗
Search mode 'all'
Why it's wrong here
Search mode 'all' applies every query term with AND semantics, narrowing recall and ignoring natural-language phrasing; semantic ranking and scoring profiles address relevance instead. It tempts because 'all' sounds thorough, but it suits precise keyword lookups, not conversational queries needing broader matching.
- ✓
Scoring profiles
Why this is correct
Scoring profiles apply weighted, function-based boosts to fields and freshness at query time, so business-relevant documents rank higher. This satisfies the requirement to improve relevance for natural language queries by tuning how results are scored.
- ✗
Filters
Why it's wrong here
Filters apply Boolean constraints to already-retrieved documents; they do not analyse natural language or rank by relevance. They are tempting because filtering is genuinely useful for narrowing results by facets or metadata, and would be correct where a query needs scoping to a category, price range or date, rather than semantic ranking of free-text queries.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.