<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2022-low">
    <titleInfo>
        <title>Low-resource Neural Machine Translation with Cross-modal Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhe</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qingkai</namePart>
        <namePart type="family">Fang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpus, which is impractical for some low-resource languages. In this paper, we turn to connect several low-resource languages to a particular high-resource one by additional visual modality. Specifically, we propose a cross-modal contrastive learning method to learn a shared space for all languages, where both a coarse-grained sentence-level objective and a fine-grained token-level one are introduced. Experimental results and further analysis show that our method can effectively learn the cross-modal and cross-lingual alignment with a small amount of image-text pairs, and achieves significant improvements over the text-only baseline under both zero-shot and few-shot scenarios.</abstract>
    <identifier type="citekey">yang-etal-2022-low</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.689</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.689/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>10134</start>
            <end>10146</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Low-resource Neural Machine Translation with Cross-modal Alignment
%A Yang, Zhe
%A Fang, Qingkai
%A Feng, Yang
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F yang-etal-2022-low
%X How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpus, which is impractical for some low-resource languages. In this paper, we turn to connect several low-resource languages to a particular high-resource one by additional visual modality. Specifically, we propose a cross-modal contrastive learning method to learn a shared space for all languages, where both a coarse-grained sentence-level objective and a fine-grained token-level one are introduced. Experimental results and further analysis show that our method can effectively learn the cross-modal and cross-lingual alignment with a small amount of image-text pairs, and achieves significant improvements over the text-only baseline under both zero-shot and few-shot scenarios.
%R 10.18653/v1/2022.emnlp-main.689
%U https://aclanthology.org/2022.emnlp-main.689/
%U https://doi.org/10.18653/v1/2022.emnlp-main.689
%P 10134-10146

Markdown (Informal)

[Low-resource Neural Machine Translation with Cross-modal Alignment](https://aclanthology.org/2022.emnlp-main.689/) (Yang et al., EMNLP 2022)

• Low-resource Neural Machine Translation with Cross-modal Alignment (Yang et al., EMNLP 2022)

ACL

• Zhe Yang, Qingkai Fang, and Yang Feng. 2022. Low-resource Neural Machine Translation with Cross-modal Alignment. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10134–10146, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.