jianqunZ/Clarity-test-v1

该数据集是一个用于文本检索任务的英文单语数据集，包含多个配置，如qrels_og、qrels_changed、corpus和queries。每个配置都有特定的特征和分割，例如查询ID、文档ID、相关性评分、标题、文本等。数据集主要用于文档检索任务，包含测试集和查询集，分别有4740和20个样本。

This dataset is a monolingual text retrieval dataset, sourced from core2017, primarily used for document retrieval tasks. The dataset includes multiple configurations such as qrels_og, qrels_changed, corpus, and queries, each containing different features and splits. For example, the qrels_og and qrels_changed configurations include features like query-id, corpus-id, and score, while the corpus configuration includes features like _id, title, and text.