<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2023-improving">
    <titleInfo>
        <title>Improving Embedding Transfer for Low-Resource Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Van</namePart>
        <namePart type="given">Hien</namePart>
        <namePart type="family">Tran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenchen</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hideki</namePart>
        <namePart type="family">Tanaka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masao</namePart>
        <namePart type="family">Utiyama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Masao</namePart>
            <namePart type="family">Utiyama</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rui</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Asia-Pacific Association for Machine Translation</publisher>
            <place>
                <placeTerm type="text">Macau SAR, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Low-resource machine translation (LRMT) poses a substantial challenge due to the scarcity of parallel training data. This paper introduces a new method to improve the transfer of the embedding layer from the Parent model to the Child model in LRMT, utilizing trained token embeddings in the Parent model’s high-resource vocabulary. Our approach involves projecting all tokens into a shared semantic space and measuring the semantic similarity between tokens in the low-resource and high-resource languages. These measures are then utilized to initialize token representations in the Child model’s low-resource vocabulary. We evaluated our approach on three benchmark datasets of low-resource language pairs: Myanmar-English, Indonesian-English, and Turkish-English. The experimental results demonstrate that our method outperforms previous methods regarding translation quality. Additionally, our approach is computationally efficient, leading to reduced training time compared to prior works.</abstract>
    <identifier type="citekey">tran-etal-2023-improving</identifier>
    <location>
        <url>https://aclanthology.org/2023.mtsummit-research.11</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>123</start>
            <end>134</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Embedding Transfer for Low-Resource Machine Translation
%A Tran, Van Hien
%A Ding, Chenchen
%A Tanaka, Hideki
%A Utiyama, Masao
%Y Utiyama, Masao
%Y Wang, Rui
%S Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F tran-etal-2023-improving
%X Low-resource machine translation (LRMT) poses a substantial challenge due to the scarcity of parallel training data. This paper introduces a new method to improve the transfer of the embedding layer from the Parent model to the Child model in LRMT, utilizing trained token embeddings in the Parent model’s high-resource vocabulary. Our approach involves projecting all tokens into a shared semantic space and measuring the semantic similarity between tokens in the low-resource and high-resource languages. These measures are then utilized to initialize token representations in the Child model’s low-resource vocabulary. We evaluated our approach on three benchmark datasets of low-resource language pairs: Myanmar-English, Indonesian-English, and Turkish-English. The experimental results demonstrate that our method outperforms previous methods regarding translation quality. Additionally, our approach is computationally efficient, leading to reduced training time compared to prior works.
%U https://aclanthology.org/2023.mtsummit-research.11
%P 123-134

Markdown (Informal)

[Improving Embedding Transfer for Low-Resource Machine Translation](https://aclanthology.org/2023.mtsummit-research.11) (Tran et al., MTSummit 2023)

• Improving Embedding Transfer for Low-Resource Machine Translation (Tran et al., MTSummit 2023)

ACL

• Van Hien Tran, Chenchen Ding, Hideki Tanaka, and Masao Utiyama. 2023. Improving Embedding Transfer for Low-Resource Machine Translation. In Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pages 123–134, Macau SAR, China. Asia-Pacific Association for Machine Translation.