@inproceedings{dagan-etal-2021-co,
title = "Co-evolution of language and agents in referential games",
author = "Dagan, Gautier and
Hupkes, Dieuwke and
Bruni, Elia",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.260",
doi = "10.18653/v1/2021.eacl-main.260",
pages = "2993--3004",
abstract = "Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners. Cogswell et al. (2019) introduced cultural transmission within referential games through a changing population of agents to constrain the emerging language to be learnable. However, the resulting languages remain inherently biased by the agents{'} underlying capabilities. In this work, we introduce Language Transmission Simulator to model both cultural and architectural evolution in a population of agents. As our core contribution, we empirically show that the optimal situation is to take into account also the learning biases of the language learners and thus let language and agents co-evolve. When we allow the agent population to evolve through architectural evolution, we achieve across the board improvements on all considered metrics and surpass the gains made with cultural transmission. These results stress the importance of studying the underlying agent architecture and pave the way to investigate the co-evolution of language and agent in language emergence studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dagan-etal-2021-co">
<titleInfo>
<title>Co-evolution of language and agents in referential games</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gautier</namePart>
<namePart type="family">Dagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elia</namePart>
<namePart type="family">Bruni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-apr</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners. Cogswell et al. (2019) introduced cultural transmission within referential games through a changing population of agents to constrain the emerging language to be learnable. However, the resulting languages remain inherently biased by the agents’ underlying capabilities. In this work, we introduce Language Transmission Simulator to model both cultural and architectural evolution in a population of agents. As our core contribution, we empirically show that the optimal situation is to take into account also the learning biases of the language learners and thus let language and agents co-evolve. When we allow the agent population to evolve through architectural evolution, we achieve across the board improvements on all considered metrics and surpass the gains made with cultural transmission. These results stress the importance of studying the underlying agent architecture and pave the way to investigate the co-evolution of language and agent in language emergence studies.</abstract>
<identifier type="citekey">dagan-etal-2021-co</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.260</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.260</url>
</location>
<part>
<date>2021-apr</date>
<extent unit="page">
<start>2993</start>
<end>3004</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Co-evolution of language and agents in referential games
%A Dagan, Gautier
%A Hupkes, Dieuwke
%A Bruni, Elia
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 apr
%I Association for Computational Linguistics
%C Online
%F dagan-etal-2021-co
%X Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners. Cogswell et al. (2019) introduced cultural transmission within referential games through a changing population of agents to constrain the emerging language to be learnable. However, the resulting languages remain inherently biased by the agents’ underlying capabilities. In this work, we introduce Language Transmission Simulator to model both cultural and architectural evolution in a population of agents. As our core contribution, we empirically show that the optimal situation is to take into account also the learning biases of the language learners and thus let language and agents co-evolve. When we allow the agent population to evolve through architectural evolution, we achieve across the board improvements on all considered metrics and surpass the gains made with cultural transmission. These results stress the importance of studying the underlying agent architecture and pave the way to investigate the co-evolution of language and agent in language emergence studies.
%R 10.18653/v1/2021.eacl-main.260
%U https://aclanthology.org/2021.eacl-main.260
%U https://doi.org/10.18653/v1/2021.eacl-main.260
%P 2993-3004
Markdown (Informal)
[Co-evolution of language and agents in referential games](https://aclanthology.org/2021.eacl-main.260) (Dagan et al., EACL 2021)
ACL
- Gautier Dagan, Dieuwke Hupkes, and Elia Bruni. 2021. Co-evolution of language and agents in referential games. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2993–3004, Online. Association for Computational Linguistics.