<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kottur-etal-2017-natural">
    <titleInfo>
        <title>Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Satwik</namePart>
        <namePart type="family">Kottur</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">José</namePart>
        <namePart type="family">Moura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dhruv</namePart>
        <namePart type="family">Batra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the protocols developed by the agents, learned without any human supervision! In this paper, using a Task &amp; Talk reference game between two agents as a testbed, we present a sequence of ‘negative’ results culminating in a ‘positive’ one – showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not interpretable or compositional. In essence, we find that natural language does not emerge ‘naturally’,despite the semblance of ease of natural-language-emergence that one may gather from recent literature. We discuss how it is possible to coax the invented languages to become more and more human-like and compositional by increasing restrictions on how two agents may communicate.</abstract>
    <identifier type="citekey">kottur-etal-2017-natural</identifier>
    <identifier type="doi">10.18653/v1/D17-1321</identifier>
    <location>
        <url>https://aclanthology.org/D17-1321</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>2962</start>
            <end>2967</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog
%A Kottur, Satwik
%A Moura, José
%A Lee, Stefan
%A Batra, Dhruv
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F kottur-etal-2017-natural
%X A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the protocols developed by the agents, learned without any human supervision! In this paper, using a Task & Talk reference game between two agents as a testbed, we present a sequence of ‘negative’ results culminating in a ‘positive’ one – showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not interpretable or compositional. In essence, we find that natural language does not emerge ‘naturally’,despite the semblance of ease of natural-language-emergence that one may gather from recent literature. We discuss how it is possible to coax the invented languages to become more and more human-like and compositional by increasing restrictions on how two agents may communicate.
%R 10.18653/v1/D17-1321
%U https://aclanthology.org/D17-1321
%U https://doi.org/10.18653/v1/D17-1321
%P 2962-2967

Markdown (Informal)

[Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog](https://aclanthology.org/D17-1321) (Kottur et al., EMNLP 2017)

• Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog (Kottur et al., EMNLP 2017)

ACL

• Satwik Kottur, José Moura, Stefan Lee, and Dhruv Batra. 2017. Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2962–2967, Copenhagen, Denmark. Association for Computational Linguistics.