irds/beir_quora_dev

`beir/quora/dev`数据集由ir-datasets包提供，主要用于文本检索任务。该数据集包含5,000个查询（即主题）和7,626个相关性评估（qrels）。文档部分需要使用`irds/beir_quora`数据集。

原始信息汇总

数据集概述

数据集名称

beir/quora/dev

数据来源

• 原始数据集：irds/beir_quora

数据集内容

• queries：查询语句，共5,000条
• qrels：相关性评估，共7,626条
• docs：文档数据，来源于irds/beir_quora

数据集用途

用于文本检索任务。

数据集加载示例

python from datasets import load_dataset

queries = load_dataset(irds/beir_quora_dev, queries) for record in queries: record # {query_id: ..., text: ...}

qrels = load_dataset(irds/beir_quora_dev, qrels) for record in qrels: record # {query_id: ..., doc_id: ..., relevance: ..., iteration: ...}

引用信息

@article{Thakur2021Beir, title = "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", author = "Thakur, Nandan and Reimers, Nils and Rücklé, Andreas and Srivastava, Abhishek and Gurevych, Iryna", journal= "arXiv preprint arXiv:2104.08663", month = "4", year = "2021", url = "https://arxiv.org/abs/2104.08663", }