irds/neumarco_zh_dev_small

---
pretty_name: '`neumarco/zh/dev/small`'
viewer: false
source_datasets: ['irds/neumarco_zh']
task_categories:
- text-retrieval
---

# Dataset Card for `neumarco/zh/dev/small`

The `neumarco/zh/dev/small` dataset, provided by the [ir-datasets](https://ir-datasets.com/) package.
For more information about the dataset, see the [documentation](https://ir-datasets.com/neumarco#neumarco/zh/dev/small).

# Data

This dataset provides:
- `queries` (i.e., topics); count=6,980
- `qrels`: (relevance assessments); count=7,437

- For `docs`, use [`irds/neumarco_zh`](https://huggingface.co/datasets/irds/neumarco_zh)

## Usage

```python
from datasets import load_dataset

queries = load_dataset('irds/neumarco_zh_dev_small', 'queries')
for record in queries:
record # {'query_id': ..., 'text': ...}

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

```

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.

原始信息汇总

数据集概述

数据集名称

neumarco/zh/dev/small

数据来源

• 原始数据集：irds/neumarco_zh

数据集内容

• queries（查询）：6,980条
• qrels（相关性评估）：7,437条
• docs（文档）：使用irds/neumarco_zh数据集

数据集用途示例

python from datasets import load_dataset

加载查询数据

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

加载相关性评估数据

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