Feudal Dialogue Management with Jointly Learned Feature Extractors

Iñigo Casanueva; Paweł Budzianowski; Stefan Ultes; Florian Kreyssig; Bo-Hsiang Tseng; Yen-Chen Wu; Milica Gasic

doi:10.18653/v1/W18-5038

Feudal Dialogue Management with Jointly Learned Feature Extractors

Iñigo Casanueva, Paweł Budzianowski, Stefan Ultes, Florian Kreyssig, Bo-Hsiang Tseng, Yen-chen Wu, Milica Gašić

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Reinforcement learning (RL) is a promising dialogue policy optimisation approach, but traditional RL algorithms fail to scale to large domains. Recently, Feudal Dialogue Management (FDM), has shown to increase the scalability to large domains by decomposing the dialogue management decision into two steps, making use of the domain ontology to abstract the dialogue state in each step. In order to abstract the state space, however, previous work on FDM relies on handcrafted feature functions. In this work, we show that these feature functions can be learned jointly with the policy model while obtaining similar performance, even outperforming the handcrafted features in several environments and domains.

Anthology ID:: W18-5038
Volume:: Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
Month:: July
Year:: 2018
Address:: Melbourne, Australia
Editors:: Kazunori Komatani, Diane Litman, Kai Yu, Alex Papangelis, Lawrence Cavedon, Mikio Nakano
Venue:: SIGDIAL
SIG:: SIGDIAL
Publisher:: Association for Computational Linguistics
Note:
Pages:: 332–337
Language:
URL:: https://aclanthology.org/W18-5038/
DOI:: 10.18653/v1/W18-5038
Bibkey:
Cite (ACL):: Iñigo Casanueva, Paweł Budzianowski, Stefan Ultes, Florian Kreyssig, Bo-Hsiang Tseng, Yen-chen Wu, and Milica Gašić. 2018. Feudal Dialogue Management with Jointly Learned Feature Extractors. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 332–337, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):: Feudal Dialogue Management with Jointly Learned Feature Extractors (Casanueva et al., SIGDIAL 2018)
Copy Citation:
PDF:: https://aclanthology.org/W18-5038.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{casanueva-etal-2018-feudal-dialogue,
    title = "Feudal Dialogue Management with Jointly Learned Feature Extractors",
    author = "Casanueva, I{\~n}igo  and
      Budzianowski, Pawe{\l}  and
      Ultes, Stefan  and
      Kreyssig, Florian  and
      Tseng, Bo-Hsiang  and
      Wu, Yen-chen  and
      Ga{\v{s}}i{\'c}, Milica",
    editor = "Komatani, Kazunori  and
      Litman, Diane  and
      Yu, Kai  and
      Papangelis, Alex  and
      Cavedon, Lawrence  and
      Nakano, Mikio",
    booktitle = "Proceedings of the 19th Annual {SIG}dial Meeting on Discourse and Dialogue",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W18-5038/",
    doi = "10.18653/v1/W18-5038",
    pages = "332--337",
    abstract = "Reinforcement learning (RL) is a promising dialogue policy optimisation approach, but traditional RL algorithms fail to scale to large domains. Recently, Feudal Dialogue Management (FDM), has shown to increase the scalability to large domains by decomposing the dialogue management decision into two steps, making use of the domain ontology to abstract the dialogue state in each step. In order to abstract the state space, however, previous work on FDM relies on handcrafted feature functions. In this work, we show that these feature functions can be learned jointly with the policy model while obtaining similar performance, even outperforming the handcrafted features in several environments and domains."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="casanueva-etal-2018-feudal-dialogue">
    <titleInfo>
        <title>Feudal Dialogue Management with Jointly Learned Feature Extractors</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Iñigo</namePart>
        <namePart type="family">Casanueva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paweł</namePart>
        <namePart type="family">Budzianowski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Ultes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Florian</namePart>
        <namePart type="family">Kreyssig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bo-Hsiang</namePart>
        <namePart type="family">Tseng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yen-chen</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Milica</namePart>
        <namePart type="family">Gašić</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 19th Annual SIGdial Meeting on Discourse and Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kazunori</namePart>
            <namePart type="family">Komatani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Diane</namePart>
            <namePart type="family">Litman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">Yu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alex</namePart>
            <namePart type="family">Papangelis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lawrence</namePart>
            <namePart type="family">Cavedon</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mikio</namePart>
            <namePart type="family">Nakano</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>Reinforcement learning (RL) is a promising dialogue policy optimisation approach, but traditional RL algorithms fail to scale to large domains. Recently, Feudal Dialogue Management (FDM), has shown to increase the scalability to large domains by decomposing the dialogue management decision into two steps, making use of the domain ontology to abstract the dialogue state in each step. In order to abstract the state space, however, previous work on FDM relies on handcrafted feature functions. In this work, we show that these feature functions can be learned jointly with the policy model while obtaining similar performance, even outperforming the handcrafted features in several environments and domains.</abstract>
    <identifier type="citekey">casanueva-etal-2018-feudal-dialogue</identifier>
    <identifier type="doi">10.18653/v1/W18-5038</identifier>
    <location>
        <url>https://aclanthology.org/W18-5038/</url>
    </location>
    <part>
        <date>2018-07</date>
        <extent unit="page">
            <start>332</start>
            <end>337</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Feudal Dialogue Management with Jointly Learned Feature Extractors
%A Casanueva, Iñigo
%A Budzianowski, Paweł
%A Ultes, Stefan
%A Kreyssig, Florian
%A Tseng, Bo-Hsiang
%A Wu, Yen-chen
%A Gašić, Milica
%Y Komatani, Kazunori
%Y Litman, Diane
%Y Yu, Kai
%Y Papangelis, Alex
%Y Cavedon, Lawrence
%Y Nakano, Mikio
%S Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F casanueva-etal-2018-feudal-dialogue
%X Reinforcement learning (RL) is a promising dialogue policy optimisation approach, but traditional RL algorithms fail to scale to large domains. Recently, Feudal Dialogue Management (FDM), has shown to increase the scalability to large domains by decomposing the dialogue management decision into two steps, making use of the domain ontology to abstract the dialogue state in each step. In order to abstract the state space, however, previous work on FDM relies on handcrafted feature functions. In this work, we show that these feature functions can be learned jointly with the policy model while obtaining similar performance, even outperforming the handcrafted features in several environments and domains.
%R 10.18653/v1/W18-5038
%U https://aclanthology.org/W18-5038/
%U https://doi.org/10.18653/v1/W18-5038
%P 332-337

Download as File

Markdown (Informal)

[Feudal Dialogue Management with Jointly Learned Feature Extractors](https://aclanthology.org/W18-5038/) (Casanueva et al., SIGDIAL 2018)

Feudal Dialogue Management with Jointly Learned Feature Extractors (Casanueva et al., SIGDIAL 2018)

ACL

Iñigo Casanueva, Paweł Budzianowski, Stefan Ultes, Florian Kreyssig, Bo-Hsiang Tseng, Yen-chen Wu, and Milica Gašić. 2018. Feudal Dialogue Management with Jointly Learned Feature Extractors. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 332–337, Melbourne, Australia. Association for Computational Linguistics.