<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-character">
    <titleInfo>
        <title>Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pinzhen</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nikolay</namePart>
        <namePart type="family">Bogoychev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ulrich</namePart>
        <namePart type="family">Germann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th International Conference on Spoken Language Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes the University of Edinburgh’s neural machine translation systems submitted to the IWSLT 2020 open domain JapanesełeftrightarrowChinese translation task. On top of commonplace techniques like tokenisation and corpus cleaning, we explore character mapping and unsupervised decoding-time adaptation. Our techniques focus on leveraging the provided data, and we show the positive impact of each technique through the gradual improvement of BLEU.</abstract>
    <identifier type="citekey">chen-etal-2020-character</identifier>
    <identifier type="doi">10.18653/v1/2020.iwslt-1.14</identifier>
    <location>
        <url>https://aclanthology.org/2020.iwslt-1.14</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>122</start>
            <end>129</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System
%A Chen, Pinzhen
%A Bogoychev, Nikolay
%A Germann, Ulrich
%S Proceedings of the 17th International Conference on Spoken Language Translation
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F chen-etal-2020-character
%X This paper describes the University of Edinburgh’s neural machine translation systems submitted to the IWSLT 2020 open domain JapanesełeftrightarrowChinese translation task. On top of commonplace techniques like tokenisation and corpus cleaning, we explore character mapping and unsupervised decoding-time adaptation. Our techniques focus on leveraging the provided data, and we show the positive impact of each technique through the gradual improvement of BLEU.
%R 10.18653/v1/2020.iwslt-1.14
%U https://aclanthology.org/2020.iwslt-1.14
%U https://doi.org/10.18653/v1/2020.iwslt-1.14
%P 122-129

Markdown (Informal)

[Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System](https://aclanthology.org/2020.iwslt-1.14) (Chen et al., IWSLT 2020)

• Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System (Chen et al., IWSLT 2020)

ACL

• Pinzhen Chen, Nikolay Bogoychev, and Ulrich Germann. 2020. Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 122–129, Online. Association for Computational Linguistics.