arXiv · 2022-10-18
Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages
פתיחת רשומת הראיות
שאלת המחקר
How can a retrieval benchmark cover languages with very different resource levels while using native queries and relevance judgments?
שיטה
An 18-language, same-language Wikipedia retrieval benchmark built with native-speaker queries and judgments; lexical, dense and hybrid baselines were compared on the released pools.
מה הראיות תומכות
Evaluate each language explicitly, document corpus and judgment construction, and keep native review central. The reported hybrid result is a historical benchmark observation.
מגבלות והעברה
This is same-language information retrieval, not translation assessment or web SEO. Heuristic segmentation, candidate-pool gaps and unfinished test labels limit transferability; it says nothing about hreflang or Google rankings.
סיווג הטענות
- נתמך
- היסטורי
- אקדמי בלבד
השפעה על NAVINES: מעבדת השוואת עמודים רב־לשוניים