@inproceedings{dai-futrell-2021-simple,
title = "Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent",
author = "Dai, Huteng and
Futrell, Richard",
editor = "Nicolai, Garrett and
Gorman, Kyle and
Cotterell, Ryan",
booktitle = "Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigmorphon-1.19",
doi = "10.18653/v1/2021.sigmorphon-1.19",
pages = "167--176",
abstract = "We introduce a simple and highly general phonotactic learner which induces a probabilistic finite-state automaton from word-form data. We describe the learner and show how to parameterize it to induce unrestricted regular languages, as well as how to restrict it to certain subregular classes such as Strictly k-Local and Strictly k-Piecewise languages. We evaluate the learner on its ability to learn phonotactic constraints in toy examples and in datasets of Quechua and Navajo. We find that an unrestricted learner is the most accurate overall when modeling attested forms not seen in training; however, only the learner restricted to the Strictly Piecewise language class successfully captures certain nonlocal phonotactic constraints. Our learner serves as a baseline for more sophisticated methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dai-futrell-2021-simple">
<titleInfo>
<title>Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huteng</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Futrell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a simple and highly general phonotactic learner which induces a probabilistic finite-state automaton from word-form data. We describe the learner and show how to parameterize it to induce unrestricted regular languages, as well as how to restrict it to certain subregular classes such as Strictly k-Local and Strictly k-Piecewise languages. We evaluate the learner on its ability to learn phonotactic constraints in toy examples and in datasets of Quechua and Navajo. We find that an unrestricted learner is the most accurate overall when modeling attested forms not seen in training; however, only the learner restricted to the Strictly Piecewise language class successfully captures certain nonlocal phonotactic constraints. Our learner serves as a baseline for more sophisticated methods.</abstract>
<identifier type="citekey">dai-futrell-2021-simple</identifier>
<identifier type="doi">10.18653/v1/2021.sigmorphon-1.19</identifier>
<location>
<url>https://aclanthology.org/2021.sigmorphon-1.19</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>167</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent
%A Dai, Huteng
%A Futrell, Richard
%Y Nicolai, Garrett
%Y Gorman, Kyle
%Y Cotterell, Ryan
%S Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F dai-futrell-2021-simple
%X We introduce a simple and highly general phonotactic learner which induces a probabilistic finite-state automaton from word-form data. We describe the learner and show how to parameterize it to induce unrestricted regular languages, as well as how to restrict it to certain subregular classes such as Strictly k-Local and Strictly k-Piecewise languages. We evaluate the learner on its ability to learn phonotactic constraints in toy examples and in datasets of Quechua and Navajo. We find that an unrestricted learner is the most accurate overall when modeling attested forms not seen in training; however, only the learner restricted to the Strictly Piecewise language class successfully captures certain nonlocal phonotactic constraints. Our learner serves as a baseline for more sophisticated methods.
%R 10.18653/v1/2021.sigmorphon-1.19
%U https://aclanthology.org/2021.sigmorphon-1.19
%U https://doi.org/10.18653/v1/2021.sigmorphon-1.19
%P 167-176
Markdown (Informal)
[Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent](https://aclanthology.org/2021.sigmorphon-1.19) (Dai & Futrell, SIGMORPHON 2021)
ACL