@inproceedings{zare-etal-2020-dialogue,
title = "Dialogue Policies for Learning Board Games through Multimodal Communication",
author = "Zare, Maryam and
Ayub, Ali and
Liu, Aishan and
Sudhakara, Sweekar and
Wagner, Alan and
Passonneau, Rebecca",
editor = "Pietquin, Olivier and
Muresan, Smaranda and
Chen, Vivian and
Kennington, Casey and
Vandyke, David and
Dethlefs, Nina and
Inoue, Koji and
Ekstedt, Erik and
Ultes, Stefan",
booktitle = "Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2020",
address = "1st virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sigdial-1.41",
doi = "10.18653/v1/2020.sigdial-1.41",
pages = "339--351",
abstract = "This paper presents MDP policy learning for agents to learn strategic behavior{--}how to play board games{--}during multimodal dialogues. Policies are trained offline in simulation, with dialogues carried out in a formal language. The agent has a temporary belief state for the dialogue, and a persistent knowledge store represented as an extensive-form game tree. How well the agent learns a new game from a dialogue with a simulated partner is evaluated by how well it plays the game, given its dialogue-final knowledge state. During policy training, we control for the simulated dialogue partner{'}s level of informativeness in responding to questions. The agent learns best when its trained policy matches the current dialogue partner{'}s informativeness. We also present a novel data collection for training natural language modules. Human subjects who engaged in dialogues with a baseline system rated the system{'}s language skills as above average. Further, results confirm that human dialogue partners also vary in their informativeness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zare-etal-2020-dialogue">
<titleInfo>
<title>Dialogue Policies for Learning Board Games through Multimodal Communication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Zare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Ayub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sweekar</namePart>
<namePart type="family">Sudhakara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Wagner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Passonneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Pietquin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</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">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Ekstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">1st virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents MDP policy learning for agents to learn strategic behavior–how to play board games–during multimodal dialogues. Policies are trained offline in simulation, with dialogues carried out in a formal language. The agent has a temporary belief state for the dialogue, and a persistent knowledge store represented as an extensive-form game tree. How well the agent learns a new game from a dialogue with a simulated partner is evaluated by how well it plays the game, given its dialogue-final knowledge state. During policy training, we control for the simulated dialogue partner’s level of informativeness in responding to questions. The agent learns best when its trained policy matches the current dialogue partner’s informativeness. We also present a novel data collection for training natural language modules. Human subjects who engaged in dialogues with a baseline system rated the system’s language skills as above average. Further, results confirm that human dialogue partners also vary in their informativeness.</abstract>
<identifier type="citekey">zare-etal-2020-dialogue</identifier>
<identifier type="doi">10.18653/v1/2020.sigdial-1.41</identifier>
<location>
<url>https://aclanthology.org/2020.sigdial-1.41</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>339</start>
<end>351</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialogue Policies for Learning Board Games through Multimodal Communication
%A Zare, Maryam
%A Ayub, Ali
%A Liu, Aishan
%A Sudhakara, Sweekar
%A Wagner, Alan
%A Passonneau, Rebecca
%Y Pietquin, Olivier
%Y Muresan, Smaranda
%Y Chen, Vivian
%Y Kennington, Casey
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Inoue, Koji
%Y Ekstedt, Erik
%Y Ultes, Stefan
%S Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2020
%8 July
%I Association for Computational Linguistics
%C 1st virtual meeting
%F zare-etal-2020-dialogue
%X This paper presents MDP policy learning for agents to learn strategic behavior–how to play board games–during multimodal dialogues. Policies are trained offline in simulation, with dialogues carried out in a formal language. The agent has a temporary belief state for the dialogue, and a persistent knowledge store represented as an extensive-form game tree. How well the agent learns a new game from a dialogue with a simulated partner is evaluated by how well it plays the game, given its dialogue-final knowledge state. During policy training, we control for the simulated dialogue partner’s level of informativeness in responding to questions. The agent learns best when its trained policy matches the current dialogue partner’s informativeness. We also present a novel data collection for training natural language modules. Human subjects who engaged in dialogues with a baseline system rated the system’s language skills as above average. Further, results confirm that human dialogue partners also vary in their informativeness.
%R 10.18653/v1/2020.sigdial-1.41
%U https://aclanthology.org/2020.sigdial-1.41
%U https://doi.org/10.18653/v1/2020.sigdial-1.41
%P 339-351
Markdown (Informal)
[Dialogue Policies for Learning Board Games through Multimodal Communication](https://aclanthology.org/2020.sigdial-1.41) (Zare et al., SIGDIAL 2020)
ACL