Semantic Search QA Test Suite
Multilingual synonym-based search validation for short-term property discovery
Search Architecture
Synonym-based Semantic Search
1
Synonym Mapping
SEMANTIC_DICTIONARY maps intent concepts β multilingual aliases (EN + PT). Not a lexical keyword search.
2
Fuzzy Matching
Levenshtein distance β€ 1 for typo tolerance on words β₯ 4 characters.
3
Content-Scan Fallback
Scans all 5 language variants (en, es, fr, ar, pt) of title, description, location, and amenities.
4
Deterministic Override
Synonym layer runs BEFORE the LLM and always wins β no reliance on LLM for classification.
Test Cases (10)
| # | Query | Lang | Variation | Status | propertyType | Keywords Found |
|---|---|---|---|---|---|---|
| 1 | short term | English | Exact match | β | β | β |
| 2 | shortterm | English | Compound (no space) | β | β | β |
| 3 | curta duraΓ§Γ£o | Portuguese | Exact with accent | β | β | β |
| 4 | aluguer curta duracao | Portuguese | Without accent | β | β | β |
| 5 | vacation rental | English | Synonym | β | β | β |
| 6 | alojamento local | Portuguese | Synonym (local lodging) | β | β | β |
| 7 | shrt term | English | Typo (missing βoβ) | β | β | β |
| 8 | airbnb | English | Brand / slang | β | β | β |
| 9 | estadia curta | Portuguese | Synonym (short stay) | β | β | β |
| 10 | temporada | Portuguese | Single word (season) | β | β | β |
Debugging Checklist
