@inproceedings{zhang-etal-2023-layoutdit,
title = "{L}ayout{DIT}: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder",
author = "Zhang, Zhiyang and
Zhang, Yaping and
Liang, Yupu and
Xiang, Lu and
Zhao, Yang and
Zhou, Yu and
Zong, Chengqing",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.673",
doi = "10.18653/v1/2023.findings-emnlp.673",
pages = "10043--10053",
abstract = "Document image translation (DIT) aims to translate text embedded in images from one language to another. It is a challenging task that needs to understand visual layout with text semantics simultaneously. However, existing methods struggle to capture the crucial visual layout in real-world complex document images. In this work, we make the first attempt to incorporate layout knowledge into DIT in an end-to-end way. Specifically, we propose a novel Layout-aware end-to-end Document Image Translation (LayoutDIT) with multi-step conductive decoder. A layout-aware encoder is first introduced to model visual layout relations with raw OCR results. Then a novel multi-step conductive decoder is unified with hidden states conduction across three step-decoders to achieve the document translation step by step. Benefiting from the layout-aware end-to-end joint training, our LayoutDIT outperforms state-of-the-art methods with better parameter efficiency. Besides, we create a new multi-domain document image translation dataset to validate the model{'}s generalization. Extensive experiments show that LayoutDIT has a good generalization in diverse and complex layout scenes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-layoutdit">
<titleInfo>
<title>LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder</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">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>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Document image translation (DIT) aims to translate text embedded in images from one language to another. It is a challenging task that needs to understand visual layout with text semantics simultaneously. However, existing methods struggle to capture the crucial visual layout in real-world complex document images. In this work, we make the first attempt to incorporate layout knowledge into DIT in an end-to-end way. Specifically, we propose a novel Layout-aware end-to-end Document Image Translation (LayoutDIT) with multi-step conductive decoder. A layout-aware encoder is first introduced to model visual layout relations with raw OCR results. Then a novel multi-step conductive decoder is unified with hidden states conduction across three step-decoders to achieve the document translation step by step. Benefiting from the layout-aware end-to-end joint training, our LayoutDIT outperforms state-of-the-art methods with better parameter efficiency. Besides, we create a new multi-domain document image translation dataset to validate the model’s generalization. Extensive experiments show that LayoutDIT has a good generalization in diverse and complex layout scenes.</abstract>
<identifier type="citekey">zhang-etal-2023-layoutdit</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.673</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.673</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10043</start>
<end>10053</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder
%A Zhang, Zhiyang
%A Zhang, Yaping
%A Liang, Yupu
%A Xiang, Lu
%A Zhao, Yang
%A Zhou, Yu
%A Zong, Chengqing
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-layoutdit
%X Document image translation (DIT) aims to translate text embedded in images from one language to another. It is a challenging task that needs to understand visual layout with text semantics simultaneously. However, existing methods struggle to capture the crucial visual layout in real-world complex document images. In this work, we make the first attempt to incorporate layout knowledge into DIT in an end-to-end way. Specifically, we propose a novel Layout-aware end-to-end Document Image Translation (LayoutDIT) with multi-step conductive decoder. A layout-aware encoder is first introduced to model visual layout relations with raw OCR results. Then a novel multi-step conductive decoder is unified with hidden states conduction across three step-decoders to achieve the document translation step by step. Benefiting from the layout-aware end-to-end joint training, our LayoutDIT outperforms state-of-the-art methods with better parameter efficiency. Besides, we create a new multi-domain document image translation dataset to validate the model’s generalization. Extensive experiments show that LayoutDIT has a good generalization in diverse and complex layout scenes.
%R 10.18653/v1/2023.findings-emnlp.673
%U https://aclanthology.org/2023.findings-emnlp.673
%U https://doi.org/10.18653/v1/2023.findings-emnlp.673
%P 10043-10053
Markdown (Informal)
[LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder](https://aclanthology.org/2023.findings-emnlp.673) (Zhang et al., Findings 2023)
ACL