cambridgeltl/vsr_random

---
license: cc-by-4.0
task_categories:
- text-classification
- question-answering
language:
- en
tags:
- multimodality
- vision-and-language
pretty_name: VSR (random split)
size_categories:
- 10K<n<100K
---

# VSR: Visual Spatial Reasoning

This is the **random set** of **VSR**: *Visual Spatial Reasoning* (TACL 2023) [[paper]](https://arxiv.org/abs/2205.00363).

### Usage

```python
from datasets import load_dataset

data_files = {"train": "train.jsonl", "dev": "dev.jsonl", "test": "test.jsonl"}
dataset = load_dataset("cambridgeltl/vsr_random", data_files=data_files)
```

Note that the image files still need to be downloaded separately. See [`data/`](https://github.com/cambridgeltl/visual-spatial-reasoning/tree/master/data) for details.

Go to our [github repo](https://github.com/cambridgeltl/visual-spatial-reasoning) for more introductions.

### Citation
If you find VSR useful:
```bibtex
@article{Liu2022VisualSR,
title={Visual Spatial Reasoning},
author={Fangyu Liu and Guy Edward Toh Emerson and Nigel Collier},
journal={Transactions of the Association for Computational Linguistics},
year={2023},
}
```

原始信息汇总

数据集概述

基本信息

• 许可证: CC-BY-4.0
• 任务类别:
  • 文本分类
  • 问答
• 语言: 英语
• 标签:
  • 多模态
  • 视觉与语言
• 美观名称: VSR (随机分割)
• 大小类别: 10K<n<100K

数据集详情

• 名称: VSR: Visual Spatial Reasoning
• 描述: 这是VSR（视觉空间推理）的随机集，该数据集发表于TACL 2023。

使用方法

• 加载数据集的示例代码如下： python from datasets import load_dataset

  data_files = {"train": "train.jsonl", "dev": "dev.jsonl", "test": "test.jsonl"} dataset = load_dataset("cambridgeltl/vsr_random", data_files=data_files)

• 注意：图像文件需要单独下载。

引用信息

• 引用格式： bibtex @article{Liu2022VisualSR, title={Visual Spatial Reasoning}, author={Fangyu Liu and Guy Edward Toh Emerson and Nigel Collier}, journal={Transactions of the Association for Computational Linguistics}, year={2023}, }