@inproceedings{zhang-etal-2025-query,
title = "A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration",
author = "Zhang, Zhiyang and
Zhang, Yaping and
Liang, Yupu and
Chen, Zhiyuan and
Xiang, Lu and
Zhao, Yang and
Zhou, Yu and
Zong, Chengqing",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.372/",
doi = "10.18653/v1/2025.findings-acl.372",
pages = "7138--7149",
ISBN = "979-8-89176-256-5",
abstract = "Document Image Translation (DIT), which aims at translating documents in images from source language to the target, plays an important role in Document Intelligence. It requires a comprehensive understanding of document multi-modalities and a focused concentration on relevant textual regions during translation. However, most existing methods usually rely on the vanilla encoder-decoder paradigm, severely losing concentration on key regions that are especially crucial for complex-layout document translation. To tackle this issue, in this paper, we propose a new Query-Response DIT framework (QRDIT). QRDIT reformulates the DIT task into a parallel response/translation process of the multiple queries (i.e., relevant source texts), explicitly centralizing its focus toward the most relevant textual regions to ensure translation accuracy. A novel dynamic aggregation mechanism is also designed to enhance the text semantics in query features toward translation. Extensive experiments in four translation directions on three benchmarks demonstrate its state-of-the-art performance, showing significant translation quality improvements toward whole-page complex-layout document images."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-query">
<titleInfo>
<title>A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration</title>
</titleInfo>
<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">Yaping</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Zhiyuan</namePart>
<namePart type="family">Chen</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">Yang</namePart>
<namePart type="family">Zhao</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>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Document Image Translation (DIT), which aims at translating documents in images from source language to the target, plays an important role in Document Intelligence. It requires a comprehensive understanding of document multi-modalities and a focused concentration on relevant textual regions during translation. However, most existing methods usually rely on the vanilla encoder-decoder paradigm, severely losing concentration on key regions that are especially crucial for complex-layout document translation. To tackle this issue, in this paper, we propose a new Query-Response DIT framework (QRDIT). QRDIT reformulates the DIT task into a parallel response/translation process of the multiple queries (i.e., relevant source texts), explicitly centralizing its focus toward the most relevant textual regions to ensure translation accuracy. A novel dynamic aggregation mechanism is also designed to enhance the text semantics in query features toward translation. Extensive experiments in four translation directions on three benchmarks demonstrate its state-of-the-art performance, showing significant translation quality improvements toward whole-page complex-layout document images.</abstract>
<identifier type="citekey">zhang-etal-2025-query</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.372</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.372/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>7138</start>
<end>7149</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration
%A Zhang, Zhiyang
%A Zhang, Yaping
%A Liang, Yupu
%A Chen, Zhiyuan
%A Xiang, Lu
%A Zhao, Yang
%A Zhou, Yu
%A Zong, Chengqing
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhang-etal-2025-query
%X Document Image Translation (DIT), which aims at translating documents in images from source language to the target, plays an important role in Document Intelligence. It requires a comprehensive understanding of document multi-modalities and a focused concentration on relevant textual regions during translation. However, most existing methods usually rely on the vanilla encoder-decoder paradigm, severely losing concentration on key regions that are especially crucial for complex-layout document translation. To tackle this issue, in this paper, we propose a new Query-Response DIT framework (QRDIT). QRDIT reformulates the DIT task into a parallel response/translation process of the multiple queries (i.e., relevant source texts), explicitly centralizing its focus toward the most relevant textual regions to ensure translation accuracy. A novel dynamic aggregation mechanism is also designed to enhance the text semantics in query features toward translation. Extensive experiments in four translation directions on three benchmarks demonstrate its state-of-the-art performance, showing significant translation quality improvements toward whole-page complex-layout document images.
%R 10.18653/v1/2025.findings-acl.372
%U https://aclanthology.org/2025.findings-acl.372/
%U https://doi.org/10.18653/v1/2025.findings-acl.372
%P 7138-7149
Markdown (Informal)
[A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration](https://aclanthology.org/2025.findings-acl.372/) (Zhang et al., Findings 2025)
ACL
- Zhiyang Zhang, Yaping Zhang, Yupu Liang, Zhiyuan Chen, Lu Xiang, Yang Zhao, Yu Zhou, and Chengqing Zong. 2025. A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration. In Findings of the Association for Computational Linguistics: ACL 2025, pages 7138–7149, Vienna, Austria. Association for Computational Linguistics.