mteb/RuSciBenchCiteRetrieval
收藏Hugging Face2025-10-21 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/mteb/RuSciBenchCiteRetrieval
下载链接
链接失效反馈官方服务：
资源简介：
这是一个科学论文直接引用预测的数据集，旨在从大量论文中检索出被查询论文直接引用的论文。数据集包含3000篇查询论文、15000篇相关（被引用）论文和75000篇不相关论文。数据集同时支持俄语和英语。它是MTEB（大规模文本嵌入基准）的一部分，并基于mlsa-iai-msu-lab/ru_sci_bench_cite_retrieval数据集。
This dataset is focused on the task of Direct Citation Prediction for scientific papers, aiming to retrieve papers that are directly cited by a given query paper from a large corpus of papers. The dataset includes 3,000 query papers, 15,000 relevant (cited) papers, and 75,000 irrelevant papers. It is available in both Russian and English. The dataset is part of the MTEB (Massive Text Embedding Benchmark) and is adapted from the mlsa-iai-msu-lab/ru_sci_bench_cite_retrieval dataset.
提供机构：
mteb
