mteb/CrossLingualSemanticDiscriminationWMT21

该数据集是一个德语-法语语料库，包含deu-fra-corpus、deu-fra-qrels和deu-fra-queries三个部分。deu-fra-corpus部分包含文本和标题，deu-fra-qrels部分包含查询ID、语料库ID和分数，deu-fra-queries部分包含查询文本。数据集提供了测试分割的数据，可用于测试和评估相关模型的性能。The dataset is a German-French corpus consisting of three parts: deu-fra-corpus, deu-fra-qrels, and deu-fra-queries. The deu-fra-corpus part contains text and titles, the deu-fra-qrels part contains query IDs, corpus IDs, and scores, and the deu-fra-queries part contains query texts. The dataset provides test split data for testing and evaluating the performance of related models.