<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-yu-2019-domain">
    <titleInfo>
        <title>Domain Adaptive Dialog Generation via Meta Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kun</namePart>
        <namePart type="family">Qian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhou</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Domain adaptation is an essential task in dialog system building because there are so many new dialog tasks created for different needs every day. Collecting and annotating training data for these new tasks is costly since it involves real user interactions. We propose a domain adaptive dialog generation method based on meta-learning (DAML). DAML is an end-to-end trainable dialog system model that learns from multiple rich-resource tasks and then adapts to new domains with minimal training samples. We train a dialog system model using multiple rich-resource single-domain dialog data by applying the model-agnostic meta-learning algorithm to dialog domain. The model is capable of learning a competitive dialog system on a new domain with only a few training examples in an efficient manner. The two-step gradient updates in DAML enable the model to learn general features across multiple tasks. We evaluate our method on a simulated dialog dataset and achieve state-of-the-art performance, which is generalizable to new tasks.</abstract>
    <identifier type="citekey">qian-yu-2019-domain</identifier>
    <identifier type="doi">10.18653/v1/P19-1253</identifier>
    <location>
        <url>https://aclanthology.org/P19-1253</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>2639</start>
            <end>2649</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Domain Adaptive Dialog Generation via Meta Learning
%A Qian, Kun
%A Yu, Zhou
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F qian-yu-2019-domain
%X Domain adaptation is an essential task in dialog system building because there are so many new dialog tasks created for different needs every day. Collecting and annotating training data for these new tasks is costly since it involves real user interactions. We propose a domain adaptive dialog generation method based on meta-learning (DAML). DAML is an end-to-end trainable dialog system model that learns from multiple rich-resource tasks and then adapts to new domains with minimal training samples. We train a dialog system model using multiple rich-resource single-domain dialog data by applying the model-agnostic meta-learning algorithm to dialog domain. The model is capable of learning a competitive dialog system on a new domain with only a few training examples in an efficient manner. The two-step gradient updates in DAML enable the model to learn general features across multiple tasks. We evaluate our method on a simulated dialog dataset and achieve state-of-the-art performance, which is generalizable to new tasks.
%R 10.18653/v1/P19-1253
%U https://aclanthology.org/P19-1253
%U https://doi.org/10.18653/v1/P19-1253
%P 2639-2649

Markdown (Informal)

[Domain Adaptive Dialog Generation via Meta Learning](https://aclanthology.org/P19-1253) (Qian & Yu, ACL 2019)

• Domain Adaptive Dialog Generation via Meta Learning (Qian & Yu, ACL 2019)

ACL

• Kun Qian and Zhou Yu. 2019. Domain Adaptive Dialog Generation via Meta Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2639–2649, Florence, Italy. Association for Computational Linguistics.