CADIERA: benchmarks for the Aragonese language

Welcome to Cadiera! This organization contains a series of NLU benchmarks for the Aragonese language, a Romance tongue spoken in Northern Spain. They can be used to test models on their competence of the Aragonese language.

We include a series of adapted NLU benchmarks:

• XCOPA
• PAWS-X
• WNLI
• Belebele
• SIB-200
• MGSM
• SIQA

All datasets have been curated by Aragonese speakers to ensure the best quality!

The name "Cadiera" is a pun on the Aragonese name for "bench"(mark)