<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2022-specializing">
    <titleInfo>
        <title>Specializing Multi-domain NMT via Penalizing Low Mutual Information</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiyoung</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hantae</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hyunchang</namePart>
        <namePart type="family">Cho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Edward</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cheonbok</namePart>
        <namePart type="family">Park</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 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multi-domain Neural Machine Translation (NMT) trains a single model with multiple domains. It is appealing because of its efficacy in handling multiple domains within one model. An ideal multi-domain NMT learns distinctive domain characteristics simultaneously, however, grasping the domain peculiarity is a non-trivial task. In this paper, we investigate domain-specific information through the lens of mutual information (MI) and propose a new objective that penalizes low MI to become higher.Our method achieved the state-of-the-art performance among the current competitive multi-domain NMT models. Also, we show our objective promotes low MI to be higher resulting in domain-specialized multi-domain NMT.</abstract>
    <identifier type="citekey">lee-etal-2022-specializing</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.680</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.680</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>10015</start>
            <end>10026</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Specializing Multi-domain NMT via Penalizing Low Mutual Information
%A Lee, Jiyoung
%A Kim, Hantae
%A Cho, Hyunchang
%A Choi, Edward
%A Park, Cheonbok
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F lee-etal-2022-specializing
%X Multi-domain Neural Machine Translation (NMT) trains a single model with multiple domains. It is appealing because of its efficacy in handling multiple domains within one model. An ideal multi-domain NMT learns distinctive domain characteristics simultaneously, however, grasping the domain peculiarity is a non-trivial task. In this paper, we investigate domain-specific information through the lens of mutual information (MI) and propose a new objective that penalizes low MI to become higher.Our method achieved the state-of-the-art performance among the current competitive multi-domain NMT models. Also, we show our objective promotes low MI to be higher resulting in domain-specialized multi-domain NMT.
%R 10.18653/v1/2022.emnlp-main.680
%U https://aclanthology.org/2022.emnlp-main.680
%U https://doi.org/10.18653/v1/2022.emnlp-main.680
%P 10015-10026

Markdown (Informal)

[Specializing Multi-domain NMT via Penalizing Low Mutual Information](https://aclanthology.org/2022.emnlp-main.680) (Lee et al., EMNLP 2022)

• Specializing Multi-domain NMT via Penalizing Low Mutual Information (Lee et al., EMNLP 2022)

ACL

• Jiyoung Lee, Hantae Kim, Hyunchang Cho, Edward Choi, and Cheonbok Park. 2022. Specializing Multi-domain NMT via Penalizing Low Mutual Information. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10015–10026, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.