|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- yztian/PRIM |
|
|
language: |
|
|
- en |
|
|
- de |
|
|
- fr |
|
|
- cs |
|
|
- ro |
|
|
- ru |
|
|
metrics: |
|
|
- bleu |
|
|
- comet |
|
|
pipeline_tag: translation |
|
|
--- |
|
|
|
|
|
# PRIM: Towards Practical In-Image Multilingual Machine Translation (EMNLP 2025 Main) |
|
|
|
|
|
> [!NOTE] |
|
|
> 📄Paper [arXiv](https://arxiv.org/abs/2509.05146) | 💻Code [GitHub](https://github.com/BITHLP/PRIM) |
|
|
|
|
|
## Introduction |
|
|
|
|
|
This repository provides the **VisTrans model**, trained as part of our work *PRIM: Towards Practical In-Image Multilingual Machine Translation*. |
|
|
|
|
|
The VisTrans model is an end-to-end model for In-Image Machine Translation, which handles the visual text and background information in the image separately, with a two-stage training and multi-task learning strategy. |
|
|
|
|
|
The model is trained on [MTedIIMT](https://huggingface.co/datasets/yztian/MTedIIMT), and tested on [PRIM](https://huggingface.co/datasets/yztian/PRIM) (see `./PRIM` directory). It is also trained and tested on [IIMT30k](https://huggingface.co/datasets/yztian/IIMT30k) (see `./IIMT30k` directory). |
|
|
|
|
|
## Inference |
|
|
|
|
|
For inference and detailed usage instructions, please refer to our [GitHub repository](https://github.com/BITHLP/PRIM). |
|
|
|
|
|
|
|
|
## Citation |
|
|
|
|
|
If you find our work helpful, we would greatly appreciate it if you could cite our paper: |
|
|
|
|
|
```bibtex |
|
|
@misc{tian2025primpracticalinimagemultilingual, |
|
|
title={PRIM: Towards Practical In-Image Multilingual Machine Translation}, |
|
|
author={Yanzhi Tian and Zeming Liu and Zhengyang Liu and Chong Feng and Xin Li and Heyan Huang and Yuhang Guo}, |
|
|
year={2025}, |
|
|
eprint={2509.05146}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.CL}, |
|
|
url={https://arxiv.org/abs/2509.05146}, |
|
|
} |
|
|
``` |
