<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-htun-2020-gokus">
    <titleInfo>
        <title>Goku’s Participation in WAT 2020</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dongzhe</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ohnmar</namePart>
        <namePart type="family">Htun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-dec</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 7th Workshop on Asian Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper introduces our neural machine translation systems’ participation in the WAT 2020 (team ID: goku20). We participated in the (i) Patent, (ii) Business Scene Dialogue (BSD) document-level translation, (iii) Mixed-domain tasks. Regardless of simplicity, standard Transformer models have been proven to be very effective in many machine translation systems. Recently, some advanced pre-training generative models have been proposed on the basis of encoder-decoder framework. Our main focus of this work is to explore how robust Transformer models perform in translation from sentence-level to document-level, from resource-rich to low-resource languages. Additionally, we also investigated the improvement that fine-tuning on the top of pre-trained transformer-based models can achieve on various tasks.</abstract>
    <identifier type="citekey">wang-htun-2020-gokus</identifier>
    <location>
        <url>https://aclanthology.org/2020.wat-1.16</url>
    </location>
    <part>
        <date>2020-dec</date>
        <extent unit="page">
            <start>135</start>
            <end>141</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Goku’s Participation in WAT 2020
%A Wang, Dongzhe
%A Htun, Ohnmar
%S Proceedings of the 7th Workshop on Asian Translation
%D 2020
%8 dec
%I Association for Computational Linguistics
%C Suzhou, China
%F wang-htun-2020-gokus
%X This paper introduces our neural machine translation systems’ participation in the WAT 2020 (team ID: goku20). We participated in the (i) Patent, (ii) Business Scene Dialogue (BSD) document-level translation, (iii) Mixed-domain tasks. Regardless of simplicity, standard Transformer models have been proven to be very effective in many machine translation systems. Recently, some advanced pre-training generative models have been proposed on the basis of encoder-decoder framework. Our main focus of this work is to explore how robust Transformer models perform in translation from sentence-level to document-level, from resource-rich to low-resource languages. Additionally, we also investigated the improvement that fine-tuning on the top of pre-trained transformer-based models can achieve on various tasks.
%U https://aclanthology.org/2020.wat-1.16
%P 135-141

Markdown (Informal)

[Goku’s Participation in WAT 2020](https://aclanthology.org/2020.wat-1.16) (Wang & Htun, WAT 2020)

• Goku’s Participation in WAT 2020 (Wang & Htun, WAT 2020)

ACL

• Dongzhe Wang and Ohnmar Htun. 2020. Goku’s Participation in WAT 2020. In Proceedings of the 7th Workshop on Asian Translation, pages 135–141, Suzhou, China. Association for Computational Linguistics.