<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cruz-sutawika-2022-samsung">
    <titleInfo>
        <title>Samsung Research Philippines - Datasaur AI’s Submission for the WMT22 Large Scale Multilingual Translation Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="given">Christian</namePart>
        <namePart type="given">Blaise</namePart>
        <namePart type="family">Cruz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lintang</namePart>
        <namePart type="family">Sutawika</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 Seventh Conference on Machine Translation (WMT)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes the submission of the joint Samsung Research Philippines - Datasaur AI team for the WMT22 Large Scale Multilingual African Translation shared task. We approach the contest as a way to explore task composition as a solution for low-resource multilingual translation, using adapter fusion to combine multiple task adapters that learn subsets of the total translation pairs. Our final model shows performance improvements in 32 out of the 44 translation directions that we participate in when compared to a single model system trained on multiple directions at once.</abstract>
    <identifier type="citekey">cruz-sutawika-2022-samsung</identifier>
    <location>
        <url>https://aclanthology.org/2022.wmt-1.100</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>1034</start>
            <end>1038</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Samsung Research Philippines - Datasaur AI’s Submission for the WMT22 Large Scale Multilingual Translation Task
%A Cruz, Jan Christian Blaise
%A Sutawika, Lintang
%S Proceedings of the Seventh Conference on Machine Translation (WMT)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F cruz-sutawika-2022-samsung
%X This paper describes the submission of the joint Samsung Research Philippines - Datasaur AI team for the WMT22 Large Scale Multilingual African Translation shared task. We approach the contest as a way to explore task composition as a solution for low-resource multilingual translation, using adapter fusion to combine multiple task adapters that learn subsets of the total translation pairs. Our final model shows performance improvements in 32 out of the 44 translation directions that we participate in when compared to a single model system trained on multiple directions at once.
%U https://aclanthology.org/2022.wmt-1.100
%P 1034-1038

Markdown (Informal)

[Samsung Research Philippines - Datasaur AI’s Submission for the WMT22 Large Scale Multilingual Translation Task](https://aclanthology.org/2022.wmt-1.100) (Cruz & Sutawika, WMT 2022)

• Samsung Research Philippines - Datasaur AI’s Submission for the WMT22 Large Scale Multilingual Translation Task (Cruz & Sutawika, WMT 2022)

ACL

• Jan Christian Blaise Cruz and Lintang Sutawika. 2022. Samsung Research Philippines - Datasaur AI’s Submission for the WMT22 Large Scale Multilingual Translation Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 1034–1038, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.