mteb/LEMBNeedleRetrieval
收藏Hugging Face2025-05-06 更新2025-05-31 收录
下载链接:
https://hf-mirror.com/datasets/mteb/LEMBNeedleRetrieval
下载链接
链接失效反馈官方服务:
资源简介:
这是一个用于文本检索任务的数据集,特别是文档检索。它是 dwzhu/LongEmbed 数据集的 needle 子集。数据集包括注释创建者、_id、text 和 title 等特征,以及不同大小的分割。数据集是单语言的,使用英语。README 还提供了如何使用 MTEB 库在此数据集上评估嵌入模型的说明。
This dataset is described in the README file as the needle subset of the dwzhu/LongEmbed dataset. It is designed for text retrieval tasks, specifically document retrieval. The dataset includes annotations creators, features such as _id, text, and title, and different splits with varying sizes. The dataset is monolingual and uses English. The README also provides information on how to evaluate an embedding model on this dataset using the MTEB library.
提供机构:
mteb



