askatasuna/RusConTextBench
收藏Hugging Face2025-10-16 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/askatasuna/RusConTextBench
下载链接
链接失效反馈官方服务：
资源简介：
RusConText Bench数据集是一个用于自然语言处理任务的数据集，包括文本分类、标记分类、零样本分类和填空等任务。该数据集的语言为俄语，数据量在1千到1万之间。它包含了多个子集，如核心ference resolution的子集、省略表达子集等，每个子集都有特定的元数据。这个数据集被用于RusConText基准测试中，用于评分和性能评估。
The RusConText Bench Dataset is a dataset for Natural Language Processing tasks, including text classification, token classification, zero-shot classification, and fill-mask tasks. The language of the dataset is Russian, and its size ranges from 1,000 to 10,000. It includes several subsets such as coreference resolution subsets, ellipsis subsets, etc., each with specific metadata. This dataset is used for the RusConText benchmark for scoring and performance evaluation.
提供机构：
askatasuna
