@inproceedings{rita-etal-2020-lazimpa,
title = "{``}{L}az{I}mpa{''}: Lazy and Impatient neural agents learn to communicate efficiently",
author = "Rita, Mathieu and
Chaabouni, Rahma and
Dupoux, Emmanuel",
booktitle = "Proceedings of the 24th Conference on Computational Natural Language Learning",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.conll-1.26",
doi = "10.18653/v1/2020.conll-1.26",
pages = "335--343",
abstract = "Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length. Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages. Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified. We hence introduce a new communication system, {``}LazImpa{''}, where the speaker is made increasingly lazy, i.e., avoids long messages, and the listener impatient, i.e., seeks to guess the intended content as soon as possible.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rita-etal-2020-lazimpa">
<titleInfo>
<title>“LazImpa”: Lazy and Impatient neural agents learn to communicate efficiently</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Rita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahma</namePart>
<namePart type="family">Chaabouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Dupoux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Conference on Computational Natural Language Learning</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>Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length. Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages. Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified. We hence introduce a new communication system, “LazImpa”, where the speaker is made increasingly lazy, i.e., avoids long messages, and the listener impatient, i.e., seeks to guess the intended content as soon as possible.</abstract>
<identifier type="citekey">rita-etal-2020-lazimpa</identifier>
<identifier type="doi">10.18653/v1/2020.conll-1.26</identifier>
<location>
<url>https://aclanthology.org/2020.conll-1.26</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>335</start>
<end>343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “LazImpa”: Lazy and Impatient neural agents learn to communicate efficiently
%A Rita, Mathieu
%A Chaabouni, Rahma
%A Dupoux, Emmanuel
%S Proceedings of the 24th Conference on Computational Natural Language Learning
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F rita-etal-2020-lazimpa
%X Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length. Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages. Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified. We hence introduce a new communication system, “LazImpa”, where the speaker is made increasingly lazy, i.e., avoids long messages, and the listener impatient, i.e., seeks to guess the intended content as soon as possible.
%R 10.18653/v1/2020.conll-1.26
%U https://aclanthology.org/2020.conll-1.26
%U https://doi.org/10.18653/v1/2020.conll-1.26
%P 335-343
Markdown (Informal)
[“LazImpa”: Lazy and Impatient neural agents learn to communicate efficiently](https://aclanthology.org/2020.conll-1.26) (Rita et al., CoNLL 2020)
ACL