mteb/NeuCLIR2022Retrieval_rus_top_250_only_w_correct-v2
收藏数据链接：
官方服务：
资源简介：
该数据集包含三个配置：语料库（corpus）、默认（default）和查询（queries）。语料库配置具有唯一标识符、文本和标题特征。默认配置具有查询标识符、语料库标识符和分数特征。查询配置具有唯一标识符和文本特征。每个配置都为测试集划分了数据。此外，还提供了每个配置的数据集大小和下载大小。
The dataset consists of three configurations: corpus, default, and queries. The corpus configuration has features for unique identifier, text, and title. The default configuration has features for query identifier, corpus identifier, and score. The queries configuration includes features for unique identifier and text. Each configuration is split specifically for the test set. Dataset sizes and download sizes are provided for each configuration.
提供机构：
mteb
