<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2019-budgeted">
    <titleInfo>
        <title>Budgeted Policy Learning for Task-Oriented Dialogue Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhirui</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiujun</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianfeng</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Enhong</namePart>
        <namePart type="family">Chen</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>This paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions (budget) for learning task-oriented dialogue agents. BCS consists of (1) a Poisson-based global scheduler to allocate budget over different stages of training; (2) a controller to decide at each training step whether the agent is trained using real or simulated experiences; (3) a user goal sampling module to generate the experiences that are most effective for policy learning. Experiments on a movie-ticket booking task with simulated and real users show that our approach leads to significant improvements in success rate over the state-of-the-art baselines given the fixed budget.</abstract>
    <identifier type="citekey">zhang-etal-2019-budgeted</identifier>
    <identifier type="doi">10.18653/v1/P19-1364</identifier>
    <location>
        <url>https://aclanthology.org/P19-1364</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>3742</start>
            <end>3751</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Budgeted Policy Learning for Task-Oriented Dialogue Systems
%A Zhang, Zhirui
%A Li, Xiujun
%A Gao, Jianfeng
%A Chen, Enhong
%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 zhang-etal-2019-budgeted
%X This paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions (budget) for learning task-oriented dialogue agents. BCS consists of (1) a Poisson-based global scheduler to allocate budget over different stages of training; (2) a controller to decide at each training step whether the agent is trained using real or simulated experiences; (3) a user goal sampling module to generate the experiences that are most effective for policy learning. Experiments on a movie-ticket booking task with simulated and real users show that our approach leads to significant improvements in success rate over the state-of-the-art baselines given the fixed budget.
%R 10.18653/v1/P19-1364
%U https://aclanthology.org/P19-1364
%U https://doi.org/10.18653/v1/P19-1364
%P 3742-3751

Markdown (Informal)

[Budgeted Policy Learning for Task-Oriented Dialogue Systems](https://aclanthology.org/P19-1364) (Zhang et al., ACL 2019)

• Budgeted Policy Learning for Task-Oriented Dialogue Systems (Zhang et al., ACL 2019)

ACL

• Zhirui Zhang, Xiujun Li, Jianfeng Gao, and Enhong Chen. 2019. Budgeted Policy Learning for Task-Oriented Dialogue Systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3742–3751, Florence, Italy. Association for Computational Linguistics.