https://github.com/adapter-hub/xgqa
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.1%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: adapter-hub
- Default Branch: master
- Size: 8.77 MB
Statistics
- Stars: 26
- Watchers: 3
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
xGQA
This reporistory contains the test-dev data of the paper "xGQA: Cross-lingual Visual Question Answering".
xGQA builds on the original work of Hudson et al. 2019: GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering. The training data can be downloaded here.
Overview
The repository is structured as follows:
- data/zero_shot/ contains the xGQA test-dev files for all 8 languages
- data/few_shot/ contains the new standard splits for few shot learning. The number in the file name indicates how many distinct images the split includes. i.e. train_10.json implies that this subset contains questions about 10 distinct images.
Training Data
Please download the English training data of GQA (Hudson et al. 2019) here.
Zero-Shot Results
Zero-shot transfer results on xGQA when transferring from English GQA. Average accuracy is reported. Mean scores are not averaged over the source language (English). | model | en | de | pt | ru | id | bn | ko | zh | mean | |-----------|:-----:|:-----:|:-----:|:-----:|:-----:|:-----:|:-----:|:-----:|:-----:| | M3P | 58.43 | 23.93 | 24.37 | 20.37 | 22.57 | 15.83 | 16.90 | 18.60 | 20.37| | OSCAR+Emb | 62.23 | 17.35 | 19.25 | 10.52 | 18.26 | 14.93 | 17.10 | 16.41 | 16.26| | OSCAR+Ada | 60.30 | 18.91 | 27.02 | 17.50 | 18.77 | 15.42 | 15.28 | 14.96 | 18.27| | mBERTAda | 56.25 | 29.76 | 30.37 | 24.42 | 19.15 | 15.12 | 19.09 | 24.86 | 23.25|
Few-Shot
Few-shot dataset sizes. The GQA test-dev set is split into new development, test sets, and training splits of different sizes. We maintain the distribution of structural types in each split. | Set | Test | Dev | Train | | | | | | |------------|:----:|:----:|:-----:|-----|-----|-----|-----|------| | #Images | 300 | 50 | 1 | 5 | 10 | 20 | 25 | 48 | | #Questions | 9666 | 1422 | 27 | 155 | 317 | 594 | 704 | 1490 |
Citation
If you find this repository helpful, please cite our paper "xGQA: Cross-lingual Visual Question Answering":
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",
}
Shield: 
This work is licensed under a Creative Commons Attribution 4.0 International License.
Owner
- Name: AdapterHub
- Login: adapter-hub
- Kind: organization
- Location: Germany
- Website: https://AdapterHub.ml
- Twitter: AdapterHub
- Repositories: 5
- Profile: https://github.com/adapter-hub
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1
Issues and Pull Requests
Last synced: about 1 year ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0