<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="michel-neubig-2018-extreme">
    <titleInfo>
        <title>Extreme Adaptation for Personalized Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Paul</namePart>
        <namePart type="family">Michel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Iryna</namePart>
            <namePart type="family">Gurevych</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yusuke</namePart>
            <namePart type="family">Miyao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Melbourne, Australia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Every person speaks or writes their own flavor of their native language, influenced by a number of factors: the content they tend to talk about, their gender, their social status, or their geographical origin. When attempting to perform Machine Translation (MT), these variations have a significant effect on how the system should perform translation, but this is not captured well by standard one-size-fits-all models. In this paper, we propose a simple and parameter-efficient adaptation technique that only requires adapting the bias of the output softmax to each particular user of the MT system, either directly or through a factored approximation. Experiments on TED talks in three languages demonstrate improvements in translation accuracy, and better reflection of speaker traits in the target text.</abstract>
    <identifier type="citekey">michel-neubig-2018-extreme</identifier>
    <identifier type="doi">10.18653/v1/P18-2050</identifier>
    <location>
        <url>https://aclanthology.org/P18-2050</url>
    </location>
    <part>
        <date>2018-07</date>
        <extent unit="page">
            <start>312</start>
            <end>318</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Extreme Adaptation for Personalized Neural Machine Translation
%A Michel, Paul
%A Neubig, Graham
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F michel-neubig-2018-extreme
%X Every person speaks or writes their own flavor of their native language, influenced by a number of factors: the content they tend to talk about, their gender, their social status, or their geographical origin. When attempting to perform Machine Translation (MT), these variations have a significant effect on how the system should perform translation, but this is not captured well by standard one-size-fits-all models. In this paper, we propose a simple and parameter-efficient adaptation technique that only requires adapting the bias of the output softmax to each particular user of the MT system, either directly or through a factored approximation. Experiments on TED talks in three languages demonstrate improvements in translation accuracy, and better reflection of speaker traits in the target text.
%R 10.18653/v1/P18-2050
%U https://aclanthology.org/P18-2050
%U https://doi.org/10.18653/v1/P18-2050
%P 312-318

Markdown (Informal)

[Extreme Adaptation for Personalized Neural Machine Translation](https://aclanthology.org/P18-2050) (Michel & Neubig, ACL 2018)

• Extreme Adaptation for Personalized Neural Machine Translation (Michel & Neubig, ACL 2018)

ACL

• Paul Michel and Graham Neubig. 2018. Extreme Adaptation for Personalized Neural Machine Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 312–318, Melbourne, Australia. Association for Computational Linguistics.