@inproceedings{garcia-etal-2022-disentangling,
title = "Disentangling Categorization in Multi-agent Emergent Communication",
author = "Garcia, Washington and
Clouse, Hamilton and
Butler, Kevin",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.335",
doi = "10.18653/v1/2022.naacl-main.335",
pages = "4523--4540",
abstract = "The emergence of language between artificial agents is a recent focus of computational linguistics, as it offers a synthetic substrate for reasoning about human language evolution. From the perspective of cognitive science, sophisticated categorization in humans is thought to enable reasoning about novel observations, and thus compose old information to describe new phenomena. Unfortunately, the literature to date has not managed to isolate the effect of categorization power in artificial agents on their inter-communication ability, particularly on novel, unseen objects. In this work, we propose the use of disentangled representations from representation learning to quantify the categorization power of agents, enabling a differential analysis between combinations of heterogeneous systems, e.g., pairs of agents which learn to communicate despite mismatched concept realization. Through this approach, we observe that agent heterogeneity can cut signaling accuracy by up to 40{\%}, despite encouraging compositionality in the artificial language. We conclude that the reasoning process of agents plays a key role in their communication, with unexpected benefits arising from their mixing, such as better language compositionality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-etal-2022-disentangling">
<titleInfo>
<title>Disentangling Categorization in Multi-agent Emergent Communication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Washington</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamilton</namePart>
<namePart type="family">Clouse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Butler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The emergence of language between artificial agents is a recent focus of computational linguistics, as it offers a synthetic substrate for reasoning about human language evolution. From the perspective of cognitive science, sophisticated categorization in humans is thought to enable reasoning about novel observations, and thus compose old information to describe new phenomena. Unfortunately, the literature to date has not managed to isolate the effect of categorization power in artificial agents on their inter-communication ability, particularly on novel, unseen objects. In this work, we propose the use of disentangled representations from representation learning to quantify the categorization power of agents, enabling a differential analysis between combinations of heterogeneous systems, e.g., pairs of agents which learn to communicate despite mismatched concept realization. Through this approach, we observe that agent heterogeneity can cut signaling accuracy by up to 40%, despite encouraging compositionality in the artificial language. We conclude that the reasoning process of agents plays a key role in their communication, with unexpected benefits arising from their mixing, such as better language compositionality.</abstract>
<identifier type="citekey">garcia-etal-2022-disentangling</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.335</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.335</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>4523</start>
<end>4540</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disentangling Categorization in Multi-agent Emergent Communication
%A Garcia, Washington
%A Clouse, Hamilton
%A Butler, Kevin
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F garcia-etal-2022-disentangling
%X The emergence of language between artificial agents is a recent focus of computational linguistics, as it offers a synthetic substrate for reasoning about human language evolution. From the perspective of cognitive science, sophisticated categorization in humans is thought to enable reasoning about novel observations, and thus compose old information to describe new phenomena. Unfortunately, the literature to date has not managed to isolate the effect of categorization power in artificial agents on their inter-communication ability, particularly on novel, unseen objects. In this work, we propose the use of disentangled representations from representation learning to quantify the categorization power of agents, enabling a differential analysis between combinations of heterogeneous systems, e.g., pairs of agents which learn to communicate despite mismatched concept realization. Through this approach, we observe that agent heterogeneity can cut signaling accuracy by up to 40%, despite encouraging compositionality in the artificial language. We conclude that the reasoning process of agents plays a key role in their communication, with unexpected benefits arising from their mixing, such as better language compositionality.
%R 10.18653/v1/2022.naacl-main.335
%U https://aclanthology.org/2022.naacl-main.335
%U https://doi.org/10.18653/v1/2022.naacl-main.335
%P 4523-4540
Markdown (Informal)
[Disentangling Categorization in Multi-agent Emergent Communication](https://aclanthology.org/2022.naacl-main.335) (Garcia et al., NAACL 2022)
ACL
- Washington Garcia, Hamilton Clouse, and Kevin Butler. 2022. Disentangling Categorization in Multi-agent Emergent Communication. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4523–4540, Seattle, United States. Association for Computational Linguistics.