@inproceedings{cordier-etal-2022-graph,
title = "Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues",
author = "Cordier, Thibault and
Urvoy, Tanguy and
Lef{\`e}vre, Fabrice and
Rojas Barahona, Lina M.",
editor = "Lemon, Oliver and
Hakkani-Tur, Dilek and
Li, Junyi Jessy and
Ashrafzadeh, Arash and
Garcia, Daniel Hern{\'a}ndez and
Alikhani, Malihe and
Vandyke, David and
Du{\v{s}}ek, Ond{\v{r}}ej",
booktitle = "Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2022",
address = "Edinburgh, UK",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sigdial-1.10",
doi = "10.18653/v1/2022.sigdial-1.10",
pages = "91--100",
abstract = "Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into account domain changes and plan over different domains/tasks in order to deal with multi-domain dialogues. However, learning with reinforcement in such context becomes difficult because the state-action dimension is larger while the reward signal remains scarce. Our experimental results suggest that structured policies based on graph neural networks combined with different degrees of imitation learning can effectively handle multi-domain dialogues. The reported experiments underline the benefit of structured policies over standard policies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cordier-etal-2022-graph">
<titleInfo>
<title>Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thibault</namePart>
<namePart type="family">Cordier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanguy</namePart>
<namePart type="family">Urvoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrice</namePart>
<namePart type="family">Lefèvre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Rojas Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Ashrafzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="given">Hernández</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Edinburgh, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into account domain changes and plan over different domains/tasks in order to deal with multi-domain dialogues. However, learning with reinforcement in such context becomes difficult because the state-action dimension is larger while the reward signal remains scarce. Our experimental results suggest that structured policies based on graph neural networks combined with different degrees of imitation learning can effectively handle multi-domain dialogues. The reported experiments underline the benefit of structured policies over standard policies.</abstract>
<identifier type="citekey">cordier-etal-2022-graph</identifier>
<identifier type="doi">10.18653/v1/2022.sigdial-1.10</identifier>
<location>
<url>https://aclanthology.org/2022.sigdial-1.10</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>91</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
%A Cordier, Thibault
%A Urvoy, Tanguy
%A Lefèvre, Fabrice
%A Rojas Barahona, Lina M.
%Y Lemon, Oliver
%Y Hakkani-Tur, Dilek
%Y Li, Junyi Jessy
%Y Ashrafzadeh, Arash
%Y Garcia, Daniel Hernández
%Y Alikhani, Malihe
%Y Vandyke, David
%Y Dušek, Ondřej
%S Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2022
%8 September
%I Association for Computational Linguistics
%C Edinburgh, UK
%F cordier-etal-2022-graph
%X Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into account domain changes and plan over different domains/tasks in order to deal with multi-domain dialogues. However, learning with reinforcement in such context becomes difficult because the state-action dimension is larger while the reward signal remains scarce. Our experimental results suggest that structured policies based on graph neural networks combined with different degrees of imitation learning can effectively handle multi-domain dialogues. The reported experiments underline the benefit of structured policies over standard policies.
%R 10.18653/v1/2022.sigdial-1.10
%U https://aclanthology.org/2022.sigdial-1.10
%U https://doi.org/10.18653/v1/2022.sigdial-1.10
%P 91-100
Markdown (Informal)
[Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues](https://aclanthology.org/2022.sigdial-1.10) (Cordier et al., SIGDIAL 2022)
ACL