mteb/MrTyDiJaRetrievalLite

Mr.TyDi是一个基于TyDi构建的多语言基准数据集，用于文档检索任务。这是日语的轻量版本，包含93,382个文档，通过5个高性能模型的硬负样本构建。数据集的任务类别包括文本检索和问答，领域涵盖百科全书、非小说和书面材料。数据集由人类标注，语言为日语，许可证为Apache-2.0。数据集包含三个配置：corpus（语料库）、qrels（查询相关文档）和queries（查询），每个配置都有详细的特征和分割信息。

Mr.TyDi is a multilingual benchmark dataset built on TyDi for document retrieval tasks. This is the lightweight Japanese version with a reduced corpus (93,382 documents) constructed using hard negatives from 5 high-performance models. The task categories include text retrieval and question answering, covering domains such as encyclopaedic, non-fiction, and written materials. The dataset is human-annotated, in Japanese language, and licensed under Apache-2.0. It includes three configurations: corpus, qrels, and queries, each with detailed features and split information.