@inproceedings{niu-etal-2024-umtit-unifying,
title = "{UMTIT}: Unifying Recognition, Translation, and Generation for Multimodal Text Image Translation",
author = "Niu, Liqiang and
Meng, Fandong and
Zhou, Jie",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1474",
pages = "16953--16972",
abstract = "Prior research in Image Machine Translation (IMT) has focused on either translating the source image solely into the target language text or exclusively into the target image. As a result, the former approach lacked the capacity to generate target images, while the latter was insufficient in producing target text. In this paper, we present a Unified Multimodal Text Image Translation (UMTIT) model that not only translates text images into the target language but also generates consistent target images. The UMTIT model consists of two image-text modality conversion steps: the first step converts images to text to recognize the source text and generate translations, while the second step transforms text to images to create target images based on the translations. Due to the limited availability of public datasets, we have constructed two multimodal image translation datasets. Experimental results show that our UMTIT model is versatile enough to handle tasks across multiple modalities and outperforms previous methods. Notably, UMTIT surpasses the state-of-the-art TrOCR in text recognition tasks, achieving a lower Character Error Rate (CER); it also outperforms cascading methods in text translation tasks, obtaining a higher BLEU score; and, most importantly, UMTIT can generate high-quality target text images.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niu-etal-2024-umtit-unifying">
<titleInfo>
<title>UMTIT: Unifying Recognition, Translation, and Generation for Multimodal Text Image Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liqiang</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prior research in Image Machine Translation (IMT) has focused on either translating the source image solely into the target language text or exclusively into the target image. As a result, the former approach lacked the capacity to generate target images, while the latter was insufficient in producing target text. In this paper, we present a Unified Multimodal Text Image Translation (UMTIT) model that not only translates text images into the target language but also generates consistent target images. The UMTIT model consists of two image-text modality conversion steps: the first step converts images to text to recognize the source text and generate translations, while the second step transforms text to images to create target images based on the translations. Due to the limited availability of public datasets, we have constructed two multimodal image translation datasets. Experimental results show that our UMTIT model is versatile enough to handle tasks across multiple modalities and outperforms previous methods. Notably, UMTIT surpasses the state-of-the-art TrOCR in text recognition tasks, achieving a lower Character Error Rate (CER); it also outperforms cascading methods in text translation tasks, obtaining a higher BLEU score; and, most importantly, UMTIT can generate high-quality target text images.</abstract>
<identifier type="citekey">niu-etal-2024-umtit-unifying</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1474</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16953</start>
<end>16972</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMTIT: Unifying Recognition, Translation, and Generation for Multimodal Text Image Translation
%A Niu, Liqiang
%A Meng, Fandong
%A Zhou, Jie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F niu-etal-2024-umtit-unifying
%X Prior research in Image Machine Translation (IMT) has focused on either translating the source image solely into the target language text or exclusively into the target image. As a result, the former approach lacked the capacity to generate target images, while the latter was insufficient in producing target text. In this paper, we present a Unified Multimodal Text Image Translation (UMTIT) model that not only translates text images into the target language but also generates consistent target images. The UMTIT model consists of two image-text modality conversion steps: the first step converts images to text to recognize the source text and generate translations, while the second step transforms text to images to create target images based on the translations. Due to the limited availability of public datasets, we have constructed two multimodal image translation datasets. Experimental results show that our UMTIT model is versatile enough to handle tasks across multiple modalities and outperforms previous methods. Notably, UMTIT surpasses the state-of-the-art TrOCR in text recognition tasks, achieving a lower Character Error Rate (CER); it also outperforms cascading methods in text translation tasks, obtaining a higher BLEU score; and, most importantly, UMTIT can generate high-quality target text images.
%U https://aclanthology.org/2024.lrec-main.1474
%P 16953-16972
Markdown (Informal)
[UMTIT: Unifying Recognition, Translation, and Generation for Multimodal Text Image Translation](https://aclanthology.org/2024.lrec-main.1474) (Niu et al., LREC-COLING 2024)
ACL