<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-kim-2018-supervised">
    <titleInfo>
        <title>Supervised Domain Enablement Attention for Personalized Domain Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Joo-Kyung</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Young-Bum</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In large-scale domain classification for natural language understanding, leveraging each user’s domain enablement information, which refers to the preferred or authenticated domains by the user, with attention mechanism has been shown to improve the overall domain classification performance. In this paper, we propose a supervised enablement attention mechanism, which utilizes sigmoid activation for the attention weighting so that the attention can be computed with more expressive power without the weight sum constraint of softmax attention. The attention weights are explicitly encouraged to be similar to the corresponding elements of the output one-hot vector, and self-distillation is used to leverage the attention information of the other enabled domains. By evaluating on the actual utterances from a large-scale IPDA, we show that our approach significantly improves domain classification performance</abstract>
    <identifier type="citekey">kim-kim-2018-supervised</identifier>
    <identifier type="doi">10.18653/v1/D18-1106</identifier>
    <location>
        <url>https://aclanthology.org/D18-1106</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>894</start>
            <end>899</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Supervised Domain Enablement Attention for Personalized Domain Classification
%A Kim, Joo-Kyung
%A Kim, Young-Bum
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F kim-kim-2018-supervised
%X In large-scale domain classification for natural language understanding, leveraging each user’s domain enablement information, which refers to the preferred or authenticated domains by the user, with attention mechanism has been shown to improve the overall domain classification performance. In this paper, we propose a supervised enablement attention mechanism, which utilizes sigmoid activation for the attention weighting so that the attention can be computed with more expressive power without the weight sum constraint of softmax attention. The attention weights are explicitly encouraged to be similar to the corresponding elements of the output one-hot vector, and self-distillation is used to leverage the attention information of the other enabled domains. By evaluating on the actual utterances from a large-scale IPDA, we show that our approach significantly improves domain classification performance
%R 10.18653/v1/D18-1106
%U https://aclanthology.org/D18-1106
%U https://doi.org/10.18653/v1/D18-1106
%P 894-899

Markdown (Informal)

[Supervised Domain Enablement Attention for Personalized Domain Classification](https://aclanthology.org/D18-1106) (Kim & Kim, EMNLP 2018)

• Supervised Domain Enablement Attention for Personalized Domain Classification (Kim & Kim, EMNLP 2018)

ACL

• Joo-Kyung Kim and Young-Bum Kim. 2018. Supervised Domain Enablement Attention for Personalized Domain Classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 894–899, Brussels, Belgium. Association for Computational Linguistics.