@article{futrell-etal-2017-generative,
title = "A Generative Model of Phonotactics",
author = "Futrell, Richard and
Albright, Adam and
Graff, Peter and
O{'}Donnell, Timothy J.",
editor = "Lee, Lillian and
Johnson, Mark and
Toutanova, Kristina",
journal = "Transactions of the Association for Computational Linguistics",
volume = "5",
year = "2017",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q17-1006",
doi = "10.1162/tacl_a_00047",
pages = "73--86",
abstract = "We present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a language. Unlike most computational models of phonotactics (Hayes and Wilson, 2008; Goldsmith and Riggle, 2012), we take a fully generative approach, modeling a process where forms are built up out of subparts by phonologically-informed structure building operations. We learn an inventory of subparts by applying stochastic memoization (Johnson et al., 2007; Goodman et al., 2008) to a generative process for phonemes structured as an and-or graph, based on concepts of feature hierarchy from generative phonology (Clements, 1985; Dresher, 2009). Subparts are combined in a way that allows tier-based feature interactions. We evaluate our models{'} ability to capture phonotactic distributions in the lexicons of 14 languages drawn from the WOLEX corpus (Graff, 2012). Our full model robustly assigns higher probabilities to held-out forms than a sophisticated N-gram model for all languages. We also present novel analyses that probe model behavior in more detail.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="futrell-etal-2017-generative">
<titleInfo>
<title>A Generative Model of Phonotactics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Futrell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Albright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Graff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="given">J</namePart>
<namePart type="family">O’Donnell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a language. Unlike most computational models of phonotactics (Hayes and Wilson, 2008; Goldsmith and Riggle, 2012), we take a fully generative approach, modeling a process where forms are built up out of subparts by phonologically-informed structure building operations. We learn an inventory of subparts by applying stochastic memoization (Johnson et al., 2007; Goodman et al., 2008) to a generative process for phonemes structured as an and-or graph, based on concepts of feature hierarchy from generative phonology (Clements, 1985; Dresher, 2009). Subparts are combined in a way that allows tier-based feature interactions. We evaluate our models’ ability to capture phonotactic distributions in the lexicons of 14 languages drawn from the WOLEX corpus (Graff, 2012). Our full model robustly assigns higher probabilities to held-out forms than a sophisticated N-gram model for all languages. We also present novel analyses that probe model behavior in more detail.</abstract>
<identifier type="citekey">futrell-etal-2017-generative</identifier>
<identifier type="doi">10.1162/tacl_a_00047</identifier>
<location>
<url>https://aclanthology.org/Q17-1006</url>
</location>
<part>
<date>2017</date>
<detail type="volume"><number>5</number></detail>
<extent unit="page">
<start>73</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T A Generative Model of Phonotactics
%A Futrell, Richard
%A Albright, Adam
%A Graff, Peter
%A O’Donnell, Timothy J.
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F futrell-etal-2017-generative
%X We present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a language. Unlike most computational models of phonotactics (Hayes and Wilson, 2008; Goldsmith and Riggle, 2012), we take a fully generative approach, modeling a process where forms are built up out of subparts by phonologically-informed structure building operations. We learn an inventory of subparts by applying stochastic memoization (Johnson et al., 2007; Goodman et al., 2008) to a generative process for phonemes structured as an and-or graph, based on concepts of feature hierarchy from generative phonology (Clements, 1985; Dresher, 2009). Subparts are combined in a way that allows tier-based feature interactions. We evaluate our models’ ability to capture phonotactic distributions in the lexicons of 14 languages drawn from the WOLEX corpus (Graff, 2012). Our full model robustly assigns higher probabilities to held-out forms than a sophisticated N-gram model for all languages. We also present novel analyses that probe model behavior in more detail.
%R 10.1162/tacl_a_00047
%U https://aclanthology.org/Q17-1006
%U https://doi.org/10.1162/tacl_a_00047
%P 73-86
Markdown (Informal)
[A Generative Model of Phonotactics](https://aclanthology.org/Q17-1006) (Futrell et al., TACL 2017)
ACL
- Richard Futrell, Adam Albright, Peter Graff, and Timothy J. O’Donnell. 2017. A Generative Model of Phonotactics. Transactions of the Association for Computational Linguistics, 5:73–86.