<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2025-text">
    <titleInfo>
        <title>From Text to Multi-Modal: Advancing Low-Resource-Language Translation through Synthetic Data Generation and Cross-Modal Alignments</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bushi</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qian</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daisy</namePart>
        <namePart type="given">Zhe</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Atul</namePart>
            <namePart type="given">Kr.</namePart>
            <namePart type="family">Ojha</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chao-hong</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Vylomova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Flammie</namePart>
            <namePart type="family">Pirinen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jonathan</namePart>
            <namePart type="family">Washington</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nathaniel</namePart>
            <namePart type="family">Oco</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xiaobing</namePart>
            <namePart type="family">Zhao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico, U.S.A.</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-230-5</identifier>
    </relatedItem>
    <abstract>In this study, we propose a novel paradigm for multi-modal low resource language dataset generation that eliminates dependency on existing parallel multi-modal datasets. Leveraging advances in large image-generation models, we introduce a systematic pipeline that transforms text-only parallel corpora into rich multi-modal translation datasets. We then validate the generated content through human evaluation. We design and implement a new MMT model framework suitable for our new generated dataset. The model contains a verification mechanism with a large language model to ensure consistency between visual content and textual translations. Experimental results across four African low-resource languages with less than 10k training corpus demonstrate significant improvements over NLLB baselines, with average gains of up to 9.8% in BLEU score and 4.3% in METEOR score. Our method shows particular effectiveness in correctly translating concrete objects and contextual elements, suggesting its potential for improving low-resource machine translation through visual grounding.</abstract>
    <identifier type="citekey">xiao-etal-2025-text</identifier>
    <identifier type="doi">10.18653/v1/2025.loresmt-1.4</identifier>
    <location>
        <url>https://aclanthology.org/2025.loresmt-1.4/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>24</start>
            <end>35</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Text to Multi-Modal: Advancing Low-Resource-Language Translation through Synthetic Data Generation and Cross-Modal Alignments
%A Xiao, Bushi
%A Shen, Qian
%A Wang, Daisy Zhe
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Zhao, Xiaobing
%S Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, U.S.A.
%@ 979-8-89176-230-5
%F xiao-etal-2025-text
%X In this study, we propose a novel paradigm for multi-modal low resource language dataset generation that eliminates dependency on existing parallel multi-modal datasets. Leveraging advances in large image-generation models, we introduce a systematic pipeline that transforms text-only parallel corpora into rich multi-modal translation datasets. We then validate the generated content through human evaluation. We design and implement a new MMT model framework suitable for our new generated dataset. The model contains a verification mechanism with a large language model to ensure consistency between visual content and textual translations. Experimental results across four African low-resource languages with less than 10k training corpus demonstrate significant improvements over NLLB baselines, with average gains of up to 9.8% in BLEU score and 4.3% in METEOR score. Our method shows particular effectiveness in correctly translating concrete objects and contextual elements, suggesting its potential for improving low-resource machine translation through visual grounding.
%R 10.18653/v1/2025.loresmt-1.4
%U https://aclanthology.org/2025.loresmt-1.4/
%U https://doi.org/10.18653/v1/2025.loresmt-1.4
%P 24-35

Markdown (Informal)

[From Text to Multi-Modal: Advancing Low-Resource-Language Translation through Synthetic Data Generation and Cross-Modal Alignments](https://aclanthology.org/2025.loresmt-1.4/) (Xiao et al., LoResMT 2025)

• From Text to Multi-Modal: Advancing Low-Resource-Language Translation through Synthetic Data Generation and Cross-Modal Alignments (Xiao et al., LoResMT 2025)

ACL

• Bushi Xiao, Qian Shen, and Daisy Zhe Wang. 2025. From Text to Multi-Modal: Advancing Low-Resource-Language Translation through Synthetic Data Generation and Cross-Modal Alignments. In Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025), pages 24–35, Albuquerque, New Mexico, U.S.A.. Association for Computational Linguistics.