arXiv · 2022-10-18
Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages
प्रमाण अभिलेख खोलें
शोध प्रश्न
How can a retrieval benchmark cover languages with very different resource levels while using native queries and relevance judgments?
विधि
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.
प्रमाण का समर्थन
Evaluate each language explicitly, document corpus and judgment construction, and keep native review central. The reported hybrid result is a historical benchmark observation.
सीमाएँ और स्थानांतरण
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.
दावा वर्गीकरण
- समर्थित
- ऐतिहासिक
- केवल अकादमिक
NAVINES पर प्रभाव: बहुभाषी पृष्ठ तुलना प्रयोगशाला