@article{sicilia-etal-2022-modeling,
title = "Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights",
author = "Sicilia, Anthony and
Maidment, Tristan and
Healy, Pat and
Alikhani, Malihe",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "10",
year = "2022",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2022.tacl-1.63",
doi = "10.1162/tacl_a_00507",
pages = "1084--1102",
abstract = "Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. Within this novel setting, we study the optimality of communication strategies for achieving this multi-task objective. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies. We also introduce a corpus of non-cooperative conversations about images in the GuessWhat?! dataset proposed by De Vries et al. (2017). We use reinforcement learning to implement multiple communication strategies in this context and find that empirical results validate our theory.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sicilia-etal-2022-modeling">
<titleInfo>
<title>Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Sicilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Maidment</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pat</namePart>
<namePart type="family">Healy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. Within this novel setting, we study the optimality of communication strategies for achieving this multi-task objective. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies. We also introduce a corpus of non-cooperative conversations about images in the GuessWhat?! dataset proposed by De Vries et al. (2017). We use reinforcement learning to implement multiple communication strategies in this context and find that empirical results validate our theory.</abstract>
<identifier type="citekey">sicilia-etal-2022-modeling</identifier>
<identifier type="doi">10.1162/tacl_a_00507</identifier>
<location>
<url>https://aclanthology.org/2022.tacl-1.63</url>
</location>
<part>
<date>2022</date>
<detail type="volume"><number>10</number></detail>
<extent unit="page">
<start>1084</start>
<end>1102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights
%A Sicilia, Anthony
%A Maidment, Tristan
%A Healy, Pat
%A Alikhani, Malihe
%J Transactions of the Association for Computational Linguistics
%D 2022
%V 10
%I MIT Press
%C Cambridge, MA
%F sicilia-etal-2022-modeling
%X Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. Within this novel setting, we study the optimality of communication strategies for achieving this multi-task objective. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies. We also introduce a corpus of non-cooperative conversations about images in the GuessWhat?! dataset proposed by De Vries et al. (2017). We use reinforcement learning to implement multiple communication strategies in this context and find that empirical results validate our theory.
%R 10.1162/tacl_a_00507
%U https://aclanthology.org/2022.tacl-1.63
%U https://doi.org/10.1162/tacl_a_00507
%P 1084-1102
Markdown (Informal)
[Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights](https://aclanthology.org/2022.tacl-1.63) (Sicilia et al., TACL 2022)
ACL