---
pretty_name: '`beir/fiqa/dev`'
viewer: false
source_datasets: ['irds/beir_fiqa']
task_categories:
- text-retrieval
---
# Dataset Card for `beir/fiqa/dev`
The `beir/fiqa/dev` dataset, provided by the [ir-datasets](https://ir-datasets.com/) package.
For more information about the dataset, see the [documentation](https://ir-datasets.com/beir#beir/fiqa/dev).
# Data
This dataset provides:
- `queries` (i.e., topics); count=500
- `qrels`: (relevance assessments); count=1,238
- For `docs`, use [`irds/beir_fiqa`](https://huggingface.co/datasets/irds/beir_fiqa)
## Usage
```python
from datasets import load_dataset
queries = load_dataset('irds/beir_fiqa_dev', 'queries')
for record in queries:
record # {'query_id': ..., 'text': ...}
qrels = load_dataset('irds/beir_fiqa_dev', '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.
## Citation Information
```
@article{Maia2018Fiqa,
title={WWW'18 Open Challenge: Financial Opinion Mining and Question Answering},
author={Macedo Maia and S. Handschuh and A. Freitas and Brian Davis and R. McDermott and M. Zarrouk and A. Balahur},
journal={Companion Proceedings of the The Web Conference 2018},
year={2018}
}
@article{Thakur2021Beir,
title = "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models",
author = "Thakur, Nandan and Reimers, Nils and Rücklé, Andreas and Srivastava, Abhishek and Gurevych, Iryna",
journal= "arXiv preprint arXiv:2104.08663",
month = "4",
year = "2021",
url = "https://arxiv.org/abs/2104.08663",
}
```
pretty_name: '`beir/fiqa/dev`'
viewer: false
source_datasets: ['irds/beir_fiqa']
task_categories:
- 文本检索（text-retrieval）
# `beir/fiqa/dev` 数据集卡片
本`beir/fiqa/dev`数据集由[ir-datasets](https://ir-datasets.com/)包提供。如需了解该数据集的更多详情，请参阅[官方文档](https://ir-datasets.com/beir#beir/fiqa/dev)。
# 数据
本数据集包含：
- `查询（queries）`（即主题）：共500条
- `相关性评估标注（qrels）`：共1238条
如需获取文档数据，请使用 [`irds/beir_fiqa`](https://huggingface.co/datasets/irds/beir_fiqa)。
## 使用方法
python
from datasets import load_dataset
queries = load_dataset('irds/beir_fiqa_dev', 'queries')
for record in queries:
record # {'query_id': ..., 'text': ...}
qrels = load_dataset('irds/beir_fiqa_dev', 'qrels')
for record in qrels:
record # {'query_id': ..., 'doc_id': ..., 'relevance': ..., 'iteration': ...}
请注意，调用`load_dataset`将下载该数据集（若数据集未公开，则会提供获取指南），并将数据转换为🤗数据集格式进行存储。
## 引用信息
@article{Maia2018Fiqa,
title={WWW'18开放挑战：金融观点挖掘与问答},
author={Macedo Maia and S. Handschuh and A. Freitas and Brian Davis and R. McDermott and M. Zarrouk and A. Balahur},
journal={2018年万维网大会Companion论文集},
year={2018}
}
@article{Thakur2021Beir,
title = "BEIR：面向信息检索模型零样本评估的异构基准",
author = "Thakur, Nandan and Reimers, Nils and Rücklé, Andreas and Srivastava, Abhishek and Gurevych, Iryna",
journal= "arXiv预印本 arXiv:2104.08663",
month = "4",
year = "2021",
url = "https://arxiv.org/abs/2104.08663",
}
