mteb/CQADupstack-Gis-PL

该数据集包含三个部分：corpus、default和queries。corpus部分包含带有标题和文本的数据，default部分包含查询ID、语料库ID和分数的数据，queries部分仅包含文本数据。数据集提供了测试集分割，可用于测试和评估模型性能。

The dataset consists of three parts: corpus, default, and queries. The corpus section includes data with titles and text, the default section includes query IDs, corpus IDs, and scores, and the queries section contains only text data. The dataset provides test set splits for testing and evaluating model performance.