five

irds/disks45_nocr_trec-robust-2004

收藏
Hugging Face2023-01-05 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/irds/disks45_nocr_trec-robust-2004
下载链接
链接失效反馈
官方服务:
资源简介:
`disks45/nocr/trec-robust-2004`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250个查询(即主题)和311,410个相关性评估(qrels)。文档部分需要从`irds/disks45_nocr`数据集中获取。数据集的使用示例代码展示了如何加载查询和相关性评估数据。此外,README还引用了相关的文献,包括NIST TREC Disks 4和5的文档集、TREC 2004 Robust Retrieval Track的概述以及关于检索模型比较的研究。

The `disks45/nocr/trec-robust-2004` dataset is provided by the ir-datasets package, and is primarily utilized for text retrieval tasks. This dataset contains 250 queries (also referred to as topics) and 311,410 relevance assessments (qrels). The document corpus needs to be obtained from the `irds/disks45_nocr` dataset. Example usage code for the dataset demonstrates how to load the query and relevance assessment data. Additionally, the README cites relevant literature, including the NIST TREC Disks 4 and 5 document collections, the overview of the TREC 2004 Robust Retrieval Track, and studies on retrieval model comparison.
提供机构:
irds
原始信息汇总

数据集概述

数据集名称

disks45/nocr/trec-robust-2004

数据来源

  • 原始数据集:irds/disks45_nocr

数据内容

  • queries: 查询(主题),数量为250。
  • qrels: 相关性评估,数量为311,410。
  • docs: 文档数据,需从irds/disks45_nocr获取。

使用示例

python from datasets import load_dataset

queries = load_dataset(irds/disks45_nocr_trec-robust-2004, queries) for record in queries: record # {query_id: ..., title: ..., description: ..., narrative: ...}

qrels = load_dataset(irds/disks45_nocr_trec-robust-2004, qrels) for record in qrels: record # {query_id: ..., doc_id: ..., relevance: ..., iteration: ...}

引用信息

@misc{Voorhees1996Disks45, title = {NIST TREC Disks 4 and 5: Retrieval Test Collections Document Set}, author = {Ellen M. Voorhees}, doi = {10.18434/t47g6m}, year = {1996}, publisher = {National Institute of Standards and Technology} } @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} }

搜集汇总
数据集介绍
main_image_url
背景与挑战
背景概述
该数据集是TREC 2004 Robust Retrieval Track的一部分,专门用于文本检索任务。它包含250个查询和311,410个相关性评估,但文档数据需从'irds/disks45_nocr'数据集获取,主要基于NIST TREC Disks 4和5文档集构建。
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务