Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling

Yupu Liang, Yaping Zhang, Cong Ma, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou


Abstract
Text image machine translation (TIMT) is a task that translates source texts embedded in the image to target translations. The existing TIMT task mainly focuses on text-line-level images. In this paper, we extend the current TIMT task and propose a novel task, **D**ocument **I**mage **M**achine **T**ranslation to **Markdown** (**DIMT2Markdown**), which aims to translate a source document image with long context and complex layout structure to markdown-formatted target translation.We also introduce a novel framework, **D**ocument **I**mage **M**achine **T**ranslation with **D**ynamic multi-pre-trained models **A**ssembling (**DIMTDA**).A dynamic model assembler is used to integrate multiple pre-trained models to enhance the model’s understanding of layout and translation capabilities.Moreover, we build a novel large-scale **Do**cument image machine **T**ranslation dataset of **A**rXiv articles in markdown format (**DoTA**), containing 126K image-translation pairs.Extensive experiments demonstrate the feasibility of end-to-end translation of rich-text document images and the effectiveness of DIMTDA.
Anthology ID:
2024.naacl-long.392
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7084–7095
Language:
URL:
https://aclanthology.org/2024.naacl-long.392
DOI:
10.18653/v1/2024.naacl-long.392
Bibkey:
Cite (ACL):
Yupu Liang, Yaping Zhang, Cong Ma, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, and Yu Zhou. 2024. Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7084–7095, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling (Liang et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.392.pdf