irds/gov2_trec-tb-2006_named-page

`gov2/trec-tb-2006/named-page`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181个查询（即主题）和2,361个相关性评估（qrels）。文档部分需要使用`irds/gov2`数据集。

The `gov2/trec-tb-2006/named-page` dataset is provided by the ir-datasets package and is primarily used for text retrieval tasks. This dataset contains 181 queries (also known as topics) and 2,361 relevance judgments (qrels). The document collection requires the use of the `irds/gov2` dataset.

原始信息汇总

数据集概述

数据集名称

gov2/trec-tb-2006/named-page

数据来源

• 原始数据集: irds/gov2

数据内容

• queries: 查询主题，数量为181
• qrels: 相关性评估，数量为2,361
• docs: 文档数据，需从irds/gov2获取

数据使用示例

python from datasets import load_dataset

queries = load_dataset(irds/gov2_trec-tb-2006_named-page, queries) for record in queries: record # {query_id: ..., text: ...}

qrels = load_dataset(irds/gov2_trec-tb-2006_named-page, qrels) for record in qrels: record # {query_id: ..., doc_id: ..., relevance: ..., iteration: ...}

引用信息

@inproceedings{Buttcher2006TrecTerabyte, title={The TREC 2006 Terabyte Track}, author={Stefan B"uttcher and Charles L. A. Clarke and Ian Soboroff}, booktitle={TREC}, year={2006} }