irds/trec-robust04_fold4
收藏资源简介:
--- pretty_name: '`trec-robust04/fold4`' viewer: false source_datasets: ['irds/trec-robust04'] task_categories: - text-retrieval --- # Dataset Card for `trec-robust04/fold4` The `trec-robust04/fold4` dataset, provided by the [ir-datasets](https://ir-datasets.com/) package. For more information about the dataset, see the [documentation](https://ir-datasets.com/trec-robust04#trec-robust04/fold4). # Data This dataset provides: - `queries` (i.e., topics); count=50 - `qrels`: (relevance assessments); count=57,962 - For `docs`, use [`irds/trec-robust04`](https://huggingface.co/datasets/irds/trec-robust04) ## Usage ```python from datasets import load_dataset queries = load_dataset('irds/trec-robust04_fold4', 'queries') for record in queries: record # {'query_id': ..., 'text': ...} qrels = load_dataset('irds/trec-robust04_fold4', 'qrels') for record in qrels: record # {'query_id': ..., 'doc_id': ..., 'relevance': ...} ``` Note that calling `load_dataset` will download the dataset (or provide access instructions when it's not public) and make a copy of the data in 🤗 Dataset format. ## Citation Information ``` @inproceedings{Voorhees2004Robust, title={Overview of the TREC 2004 Robust Retrieval Track}, author={Ellen Voorhees}, booktitle={TREC}, year={2004} } @inproceedings{Huston2014ACO, title={A Comparison of Retrieval Models using Term Dependencies}, author={Samuel Huston and W. Bruce Croft}, booktitle={CIKM}, year={2014} } ```
--- 数据集显示名:`trec-robust04/fold4` 数据集查看器:禁用 源数据集:['irds/trec-robust04'] 任务类别: - 文本检索(text-retrieval) --- # `trec-robust04/fold4` 数据集卡片 本`trec-robust04/fold4`数据集由[ir-datasets](https://ir-datasets.com/)库提供。如需了解该数据集的更多详情,请参阅[官方文档](https://ir-datasets.com/trec-robust04#trec-robust04/fold4)。 ## 数据概况 本数据集包含以下内容: - `queries`(即查询主题):共计50条 - `qrels`(相关性评估标注):共计57,962条 如需获取文档数据,请使用 [`irds/trec-robust04`](https://huggingface.co/datasets/irds/trec-robust04) 数据集。 ## 使用方法 python from datasets import load_dataset # 加载查询数据 queries = load_dataset('irds/trec-robust04_fold4', 'queries') for record in queries: record # 格式为 {'query_id': ..., 'text': ...} # 加载相关性标注数据 qrels = load_dataset('irds/trec-robust04_fold4', 'qrels') for record in qrels: record # 格式为 {'query_id': ..., 'doc_id': ..., 'relevance': ...} 请注意:调用`load_dataset`函数将自动下载该数据集(若数据集未公开,则会提供获取指引),并将数据转换为🤗 Dataset格式存储一份副本。 ## 引用信息 @inproceedings{Voorhees2004Robust, title={Overview of the TREC 2004 Robust Retrieval Track}, author={Ellen Voorhees}, booktitle={TREC}, year={2004} } @inproceedings{Huston2014ACO, title={A Comparison of Retrieval Models using Term Dependencies}, author={Samuel Huston and W. Bruce Croft}, booktitle={CIKM}, year={2014} }
数据集概述
数据集名称
trec-robust04/fold4
数据来源
- 源数据集:
irds/trec-robust04
数据内容
queries:查询(即主题),数量为50qrels:相关性评估,数量为57,962- 文档数据使用:
irds/trec-robust04
数据使用示例
python from datasets import load_dataset
queries = load_dataset(irds/trec-robust04_fold4, queries) for record in queries: record # {query_id: ..., text: ...}
qrels = load_dataset(irds/trec-robust04_fold4, qrels) for record in qrels: record # {query_id: ..., doc_id: ..., relevance: ...}
引用信息
@inproceedings{Voorhees2004Robust, title={Overview of the TREC 2004 Robust Retrieval Track}, author={Ellen Voorhees}, booktitle={TREC}, year={2004} } @inproceedings{Huston2014ACO, title={A Comparison of Retrieval Models using Term Dependencies}, author={Samuel Huston and W. Bruce Croft}, booktitle={CIKM}, year={2014} }




