HiTZ/XNLIvar
收藏Hugging Face2025-06-19 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/HiTZ/XNLIvar
下载链接
链接失效反馈官方服务：
资源简介：
XNLIvar是一个包含巴斯克语和西班牙语及其语言变体的自然语言推理（NLI）评估数据集。该数据集基于XNLI进行修改和手动校对，旨在评估当前语言技术在处理巴斯克语和西班牙语地理变体方面的性能。数据集包括原始的XNLI测试数据，以及包含本地和变体数据的数据集。
XNLIvar is a novel, manually-curated, variation-inclusive NLI dataset in Basque and Spanish for NLI evaluation. The dataset is based on the modification and manual curation of XNLI, aiming to assess the performance of current language technologies in processing geographical variants of Basque and Spanish. It includes the original XNLI test data, as well as datasets with native and variation data.
提供机构：
HiTZ
