Cross-lingual Choice of Plausible Alternatives (XCOPA)
Commonsense ReasoningMulti-Lingual
The Cross-lingual Choice of Plausible Alternatives (XCOPA) dataset is a Multi-Lingual commonsense reasoning resource from Ponti et al. at 2020.
About Cross-lingual Choice of Plausible Alternatives (XCOPA)
Dataset is the translation and reannotation of the English COPA and covers 11 languages: Estonian, Haitian Creole, Indonesian, Italian, Quechua, Swahili, Tamil, Thai, Turkish, Vietnamese & Mandarin Chinese. The dataset requires both the command of world knowledge and the ability to generalise to new languages.
Details
- Task
- Commonsense Reasoning
- Language
- Multi-Lingual
- Format
- JSON
- Rows / instances
- n/a
- Creator
- Ponti et al.
- Year
- 2020