sionic-ai/NanoBEIR-en

NanoBEIR-en是一个英文NanoBEIR基准数据集，包含预处理过的查询，用于信息检索评估。数据集分为三个部分：语料库（corpus）、查询与文档的相关性（qrels）和查询（queries）。每个部分包含多个子集，如NanoClimateFEVER、NanoDBPedia等，覆盖了不同的领域和主题。数据集适用于文本检索任务，特别适合用于句子转换模型（sentence-transformers）和NanoBEIR检索系统的评估和开发。

NanoBEIR-en is an English NanoBEIR benchmark dataset with preprocessed queries for information retrieval evaluation. The dataset is divided into three configurations: corpus (text collection), qrels (query-document relevance), and queries (search queries). Each configuration contains multiple subsets such as NanoClimateFEVER, NanoDBPedia, etc., covering various domains and topics. The dataset is designed for text retrieval tasks and is particularly suitable for evaluating and developing sentence-transformers and NanoBEIR retrieval systems.