@inproceedings{liang-etal-2024-document,
title = "Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling",
author = "Liang, Yupu and
Zhang, Yaping and
Ma, Cong and
Zhang, Zhiyang and
Zhao, Yang and
Xiang, Lu and
Zong, Chengqing and
Zhou, Yu",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.392",
doi = "10.18653/v1/2024.naacl-long.392",
pages = "7084--7095",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2024-document">
<titleInfo>
<title>Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yupu</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaping</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cong</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">liang-etal-2024-document</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.392</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.392</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>7084</start>
<end>7095</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling
%A Liang, Yupu
%A Zhang, Yaping
%A Ma, Cong
%A Zhang, Zhiyang
%A Zhao, Yang
%A Xiang, Lu
%A Zong, Chengqing
%A Zhou, Yu
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F liang-etal-2024-document
%X 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.
%R 10.18653/v1/2024.naacl-long.392
%U https://aclanthology.org/2024.naacl-long.392
%U https://doi.org/10.18653/v1/2024.naacl-long.392
%P 7084-7095
Markdown (Informal)
[Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling](https://aclanthology.org/2024.naacl-long.392) (Liang et al., NAACL 2024)
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.