irds/msmarco-document_trec-dl-hard

`msmarco-document/trec-dl-hard`数据集由`ir-datasets`包提供，包含50个查询（即主题）和8,544个相关性评估（qrels）。文档部分需要从`irds/msmarco-document`数据集中获取。该数据集主要用于文本检索任务。

The `msmarco-document/trec-dl-hard` dataset is distributed via the `ir-datasets` package, containing 50 queries (i.e., topics) and 8,544 relevance judgments (qrels). The document collection of this dataset must be obtained from the `irds/msmarco-document` dataset. This dataset is primarily used for text retrieval tasks.

原始信息汇总

数据集概述

数据集名称

msmarco-document/trec-dl-hard

数据来源

• 源数据集：irds/msmarco-document

任务类别

• 文本检索

数据内容

• queries（查询主题）：数量=50
• qrels（相关性评估）：数量=8,544
• docs（文档）：使用irds/msmarco-document数据集

使用示例

python from datasets import load_dataset

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

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

引用信息

@article{Mackie2021DlHard, title={How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset}, author={Iain Mackie and Jeffrey Dalton and Andrew Yates}, journal={ArXiv}, year={2021}, volume={abs/2105.07975} } @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} }