@inproceedings{tian-etal-2023-image,
title = "In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model",
author = "Tian, Yanzhi and
Li, Xiang and
Liu, Zeming and
Guo, Yuhang and
Wang, Bin",
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.1004",
doi = "10.18653/v1/2023.findings-emnlp.1004",
pages = "15046--15057",
abstract = "In-Image Machine Translation (IIMT) aims to convert images containing texts from one language to another. Traditional approaches for this task are cascade methods, which utilize optical character recognition (OCR) followed by neural machine translation (NMT) and text rendering. However, the cascade methods suffer from compounding errors of OCR and NMT, leading to a decrease in translation quality. In this paper, we propose an end-to-end model instead of the OCR, NMT and text rendering pipeline. Our neural architecture adopts encoder-decoder paradigm with segmented pixel sequences as inputs and outputs. Through end-to-end training, our model yields improvements across various dimensions, (i) it achieves higher translation quality by avoiding error propagation, (ii) it demonstrates robustness for out domain data, and (iii) it displays insensitivity to incomplete words. To validate the effectiveness of our method and support for future research, we construct our dataset containing 4M pairs of De-En images and train our end-to-end model. The experimental results show that our approach outperforms both cascade method and current end-to-end model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-etal-2023-image">
<titleInfo>
<title>In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanzhi</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</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>In-Image Machine Translation (IIMT) aims to convert images containing texts from one language to another. Traditional approaches for this task are cascade methods, which utilize optical character recognition (OCR) followed by neural machine translation (NMT) and text rendering. However, the cascade methods suffer from compounding errors of OCR and NMT, leading to a decrease in translation quality. In this paper, we propose an end-to-end model instead of the OCR, NMT and text rendering pipeline. Our neural architecture adopts encoder-decoder paradigm with segmented pixel sequences as inputs and outputs. Through end-to-end training, our model yields improvements across various dimensions, (i) it achieves higher translation quality by avoiding error propagation, (ii) it demonstrates robustness for out domain data, and (iii) it displays insensitivity to incomplete words. To validate the effectiveness of our method and support for future research, we construct our dataset containing 4M pairs of De-En images and train our end-to-end model. The experimental results show that our approach outperforms both cascade method and current end-to-end model.</abstract>
<identifier type="citekey">tian-etal-2023-image</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.1004</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.1004</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>15046</start>
<end>15057</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model
%A Tian, Yanzhi
%A Li, Xiang
%A Liu, Zeming
%A Guo, Yuhang
%A Wang, Bin
%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 tian-etal-2023-image
%X In-Image Machine Translation (IIMT) aims to convert images containing texts from one language to another. Traditional approaches for this task are cascade methods, which utilize optical character recognition (OCR) followed by neural machine translation (NMT) and text rendering. However, the cascade methods suffer from compounding errors of OCR and NMT, leading to a decrease in translation quality. In this paper, we propose an end-to-end model instead of the OCR, NMT and text rendering pipeline. Our neural architecture adopts encoder-decoder paradigm with segmented pixel sequences as inputs and outputs. Through end-to-end training, our model yields improvements across various dimensions, (i) it achieves higher translation quality by avoiding error propagation, (ii) it demonstrates robustness for out domain data, and (iii) it displays insensitivity to incomplete words. To validate the effectiveness of our method and support for future research, we construct our dataset containing 4M pairs of De-En images and train our end-to-end model. The experimental results show that our approach outperforms both cascade method and current end-to-end model.
%R 10.18653/v1/2023.findings-emnlp.1004
%U https://aclanthology.org/2023.findings-emnlp.1004
%U https://doi.org/10.18653/v1/2023.findings-emnlp.1004
%P 15046-15057
Markdown (Informal)
[In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model](https://aclanthology.org/2023.findings-emnlp.1004) (Tian et al., Findings 2023)
ACL