@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.",
}
<?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>
%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
Markdown (Informal)
[Feudal Dialogue Management with Jointly Learned Feature Extractors](https://aclanthology.org/W18-5038) (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.