@inproceedings{chaabouni-etal-2019-word,
title = "Word-order Biases in Deep-agent Emergent Communication",
author = "Chaabouni, Rahma and
Kharitonov, Eugene and
Lazaric, Alessandro and
Dupoux, Emmanuel and
Baroni, Marco",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1509",
doi = "10.18653/v1/P19-1509",
pages = "5166--5175",
abstract = "Sequence-processing neural networks led to remarkable progress on many NLP tasks. As a consequence, there has been increasing interest in understanding to what extent they process language as humans do. We aim here to uncover which biases such models display with respect to {``}natural{''} word-order constraints. We train models to communicate about paths in a simple gridworld, using miniature languages that reflect or violate various natural language trends, such as the tendency to avoid redundancy or to minimize long-distance dependencies. We study how the controlled characteristics of our miniature languages affect individual learning and their stability across multiple network generations. The results draw a mixed picture. On the one hand, neural networks show a strong tendency to avoid long-distance dependencies. On the other hand, there is no clear preference for the efficient, non-redundant encoding of information that is widely attested in natural language. We thus suggest inoculating a notion of {``}effort{''} into neural networks, as a possible way to make their linguistic behavior more human-like.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaabouni-etal-2019-word">
<titleInfo>
<title>Word-order Biases in Deep-agent Emergent Communication</title>
</titleInfo>
<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">Eugene</namePart>
<namePart type="family">Kharitonov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lazaric</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>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Baroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sequence-processing neural networks led to remarkable progress on many NLP tasks. As a consequence, there has been increasing interest in understanding to what extent they process language as humans do. We aim here to uncover which biases such models display with respect to “natural” word-order constraints. We train models to communicate about paths in a simple gridworld, using miniature languages that reflect or violate various natural language trends, such as the tendency to avoid redundancy or to minimize long-distance dependencies. We study how the controlled characteristics of our miniature languages affect individual learning and their stability across multiple network generations. The results draw a mixed picture. On the one hand, neural networks show a strong tendency to avoid long-distance dependencies. On the other hand, there is no clear preference for the efficient, non-redundant encoding of information that is widely attested in natural language. We thus suggest inoculating a notion of “effort” into neural networks, as a possible way to make their linguistic behavior more human-like.</abstract>
<identifier type="citekey">chaabouni-etal-2019-word</identifier>
<identifier type="doi">10.18653/v1/P19-1509</identifier>
<location>
<url>https://aclanthology.org/P19-1509</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>5166</start>
<end>5175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word-order Biases in Deep-agent Emergent Communication
%A Chaabouni, Rahma
%A Kharitonov, Eugene
%A Lazaric, Alessandro
%A Dupoux, Emmanuel
%A Baroni, Marco
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F chaabouni-etal-2019-word
%X Sequence-processing neural networks led to remarkable progress on many NLP tasks. As a consequence, there has been increasing interest in understanding to what extent they process language as humans do. We aim here to uncover which biases such models display with respect to “natural” word-order constraints. We train models to communicate about paths in a simple gridworld, using miniature languages that reflect or violate various natural language trends, such as the tendency to avoid redundancy or to minimize long-distance dependencies. We study how the controlled characteristics of our miniature languages affect individual learning and their stability across multiple network generations. The results draw a mixed picture. On the one hand, neural networks show a strong tendency to avoid long-distance dependencies. On the other hand, there is no clear preference for the efficient, non-redundant encoding of information that is widely attested in natural language. We thus suggest inoculating a notion of “effort” into neural networks, as a possible way to make their linguistic behavior more human-like.
%R 10.18653/v1/P19-1509
%U https://aclanthology.org/P19-1509
%U https://doi.org/10.18653/v1/P19-1509
%P 5166-5175
Markdown (Informal)
[Word-order Biases in Deep-agent Emergent Communication](https://aclanthology.org/P19-1509) (Chaabouni et al., ACL 2019)
ACL
- Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, and Marco Baroni. 2019. Word-order Biases in Deep-agent Emergent Communication. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5166–5175, Florence, Italy. Association for Computational Linguistics.