neulab/PangeaBench-xgqa
收藏Hugging Face2024-10-31 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/neulab/PangeaBench-xgqa
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
features:
- name: question
dtype: string
- name: answer
dtype: string
- name: full_answer
dtype: string
- name: image_id
dtype: string
- name: image
dtype: image
splits:
- name: bn
num_bytes: 498517814
num_examples: 9666
- name: de
num_bytes: 498108367
num_examples: 9666
- name: en
num_bytes: 498078827
num_examples: 9666
- name: id
num_bytes: 498180441
num_examples: 9666
- name: ko
num_bytes: 498157980
num_examples: 9666
- name: pt
num_bytes: 498078408
num_examples: 9666
- name: ru
num_bytes: 498298164
num_examples: 9666
- name: zh
num_bytes: 498005624
num_examples: 9666
download_size: 2692912777
dataset_size: 3985425625
configs:
- config_name: default
data_files:
- split: bn
path: data/bn-*
- split: de
path: data/de-*
- split: en
path: data/en-*
- split: id
path: data/id-*
- split: ko
path: data/ko-*
- split: pt
path: data/pt-*
- split: ru
path: data/ru-*
- split: zh
path: data/zh-*
license: cc-by-4.0
task_categories:
- visual-question-answering
language:
- bn
- de
- en
- id
- ko
- pt
- ru
- zh
pretty_name: xgqa
size_categories:
- 10K<n<100K
---
# xGQA
### This is a clone of the `few_shot-test` split of the xGQA dataset
Please find the original repository here: https://github.com/adapter-hub/xGQA
If you use this dataset, please cite the original authors:
```bibtex
@inproceedings{pfeiffer-etal-2021-xGQA,
title={{xGQA: Cross-Lingual Visual Question Answering}},
author={ Jonas Pfeiffer and Gregor Geigle and Aishwarya Kamath and Jan-Martin O. Steitz and Stefan Roth and Ivan Vuli{\'{c}} and Iryna Gurevych},
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = May,
year = "2022",
url = "https://arxiv.org/pdf/2109.06082.pdf",
publisher = "Association for Computational Linguistics",
}
```
数据集信息:
特征字段:
- 名称:问题(question),数据类型:字符串
- 名称:答案(answer),数据类型:字符串
- 名称:完整答案(full_answer),数据类型:字符串
- 名称:图像ID(image_id),数据类型:字符串
- 名称:图像(image),数据类型:图像
拆分集:
- 拆分名称:孟加拉语(bn),数据字节数:498517814,样本数量:9666
- 拆分名称:德语(de),数据字节数:498108367,样本数量:9666
- 拆分名称:英语(en),数据字节数:498078827,样本数量:9666
- 拆分名称:印尼语(id),数据字节数:498180441,样本数量:9666
- 拆分名称:韩语(ko),数据字节数:498157980,样本数量:9666
- 拆分名称:葡萄牙语(pt),数据字节数:498078408,样本数量:9666
- 拆分名称:俄语(ru),数据字节数:498298164,样本数量:9666
- 拆分名称:中文(zh),数据字节数:498005624,样本数量:9666
下载大小:2692912777
数据集总大小:3985425625
配置项:
- 配置名称:默认(default),数据文件:
- 拆分集:bn,路径:data/bn-*
- 拆分集:de,路径:data/de-*
- 拆分集:en,路径:data/en-*
- 拆分集:id,路径:data/id-*
- 拆分集:ko,路径:data/ko-*
- 拆分集:pt,路径:data/pt-*
- 拆分集:ru,路径:data/ru-*
- 拆分集:zh,路径:data/zh-*
许可协议:CC BY 4.0
任务类别:视觉问答(visual-question-answering)
语言:
- 孟加拉语(bn)
- 德语(de)
- 英语(en)
- 印尼语(id)
- 韩语(ko)
- 葡萄牙语(pt)
- 俄语(ru)
- 中文(zh)
友好名称:xGQA
规模类别:1万 < 样本数 < 10万
# xGQA
### 本数据集为xGQA数据集`少样本测试(few_shot-test)`拆分的复刻版本。
原始仓库地址:https://github.com/adapter-hub/xGQA
若您使用本数据集,请引用原作者的研究:
bibtex
@inproceedings{pfeiffer-etal-2021-xGQA,
title={{xGQA:跨语言视觉问答(xGQA: Cross-Lingual Visual Question Answering)}},
author={ Jonas Pfeiffer and Gregor Geigle and Aishwarya Kamath and Jan-Martin O. Steitz and Stefan Roth and Ivan Vulić and Iryna Gurevych},
booktitle = "《计算语言学协会研究发现:ACL 2022》",
month = "5月",
year = "2022",
url = "https://arxiv.org/pdf/2109.06082.pdf",
publisher = "计算语言学协会",
}
提供机构:
neulab


