irds/msmarco-passage_dev

`msmarco-passage/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101,093条查询（queries）和59,273条相关性评估（qrels）。文档部分需要使用`irds/msmarco-passage`数据集。该数据集被`msmarco-passage_dev_judged`数据集使用。

The `msmarco-passage/dev` dataset, provided by the ir-datasets package, is primarily intended for text retrieval tasks. It includes 101,093 queries and 59,273 relevance judgment pairs (qrels). The document corpus for this dataset relies on the `irds/msmarco-passage` dataset. Furthermore, this dataset is utilized by the `msmarco-passage_dev_judged` dataset.

原始信息汇总

数据集概述

数据集名称

msmarco-passage/dev

数据集来源

• 源数据集：irds/msmarco-passage
• 提供方：ir-datasets

数据集内容

• queries（查询）：101,093条
• qrels（相关性评估）：59,273条
• docs（文档）：使用irds/msmarco-passage数据集

数据集用途

用于msmarco-passage_dev_judged数据集

数据集加载示例

python from datasets import load_dataset

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

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

引用信息

@inproceedings{Bajaj2016Msmarco, title={MS MARCO: A Human Generated MAchine Reading COmprehension Dataset}, author={Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang}, booktitle={InCoCo@NIPS}, year={2016} }