@inproceedings{yang-etal-2022-low,
title = "Low-resource Neural Machine Translation with Cross-modal Alignment",
author = "Yang, Zhe and
Fang, Qingkai and
Feng, Yang",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.689/",
doi = "10.18653/v1/2022.emnlp-main.689",
pages = "10134--10146",
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."
}
<?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)
ACL