@inproceedings{pimentel-etal-2019-rethinking,
title = "Rethinking Phonotactic Complexity",
author = "Pimentel, Tiago and
Roark, Brian and
Cotterell, Ryan",
editor = "Axelrod, Amittai and
Yang, Diyi and
Cunha, Rossana and
Shaikh, Samira and
Waseem, Zeerak",
booktitle = "Proceedings of the 2019 Workshop on Widening NLP",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3628/",
pages = "88--90",
abstract = "In this work, we propose the use of phone-level language models to estimate phonotactic complexity{---}measured in bits per phoneme{---}which makes cross-linguistic comparison straightforward. We compare the entropy across languages using this simple measure, gaining insight on how complex different language`s phonotactics are. Finally, we show a very strong negative correlation between phonotactic complexity and the average length of words{---}Spearman rho=-0.744{---}when analysing a collection of 106 languages with 1016 basic concepts each."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pimentel-etal-2019-rethinking">
<titleInfo>
<title>Rethinking Phonotactic Complexity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tiago</namePart>
<namePart type="family">Pimentel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Roark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Workshop on Widening NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amittai</namePart>
<namePart type="family">Axelrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Waseem</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>In this work, we propose the use of phone-level language models to estimate phonotactic complexity—measured in bits per phoneme—which makes cross-linguistic comparison straightforward. We compare the entropy across languages using this simple measure, gaining insight on how complex different language‘s phonotactics are. Finally, we show a very strong negative correlation between phonotactic complexity and the average length of words—Spearman rho=-0.744—when analysing a collection of 106 languages with 1016 basic concepts each.</abstract>
<identifier type="citekey">pimentel-etal-2019-rethinking</identifier>
<location>
<url>https://aclanthology.org/W19-3628/</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>88</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Phonotactic Complexity
%A Pimentel, Tiago
%A Roark, Brian
%A Cotterell, Ryan
%Y Axelrod, Amittai
%Y Yang, Diyi
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Waseem, Zeerak
%S Proceedings of the 2019 Workshop on Widening NLP
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F pimentel-etal-2019-rethinking
%X In this work, we propose the use of phone-level language models to estimate phonotactic complexity—measured in bits per phoneme—which makes cross-linguistic comparison straightforward. We compare the entropy across languages using this simple measure, gaining insight on how complex different language‘s phonotactics are. Finally, we show a very strong negative correlation between phonotactic complexity and the average length of words—Spearman rho=-0.744—when analysing a collection of 106 languages with 1016 basic concepts each.
%U https://aclanthology.org/W19-3628/
%P 88-90
Markdown (Informal)
[Rethinking Phonotactic Complexity](https://aclanthology.org/W19-3628/) (Pimentel et al., WiNLP 2019)
ACL
- Tiago Pimentel, Brian Roark, and Ryan Cotterell. 2019. Rethinking Phonotactic Complexity. In Proceedings of the 2019 Workshop on Widening NLP, pages 88–90, Florence, Italy. Association for Computational Linguistics.