ViVQA: Vietnamese Question Answering Dataset - PACLIC 35

General Introduction

This repository contains the data of the paper: ViVQA: Vietnamese Visual Question Answering

ViVQA is a new dataset for evaluating Vietnamese VQA models. The ViVQA dataset consists of 10,328 images and 15,000 pairs of questions and answers in Vietnamese corresponding to the content of the images. We divide the dataset randomly into training and test sets with a ratio of 8:2.

Data Example

Citation

Please cite the following paper if you found it useful in your work.

@inproceedings{tran-etal-2021-vivqa-vietnamese,
    title = "ViVQA: Vietnamese Visual Question Answering",
    author = "Tran, Khanh Quoc  and
      Nguyen, An Trong  and
      Le, An Tran-Hoai  and
      Nguyen, Kiet Van",
    booktitle = "Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation",
    month = "11",
    year = "2021",
    address = "Shanghai, China",
    publisher = "Association for Computational Lingustics",
    url = "https://aclanthology.org/2021.paclic-1.72/",
    pages = "546--554",
}