@inproceedings{doucette-2017-inherent,
title = "Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation",
author = "Doucette, Amanda",
editor = "Gibson, Ted and
Linzen, Tal and
Sayeed, Asad and
van Schijndel, Martin and
Schuler, William",
booktitle = "Proceedings of the 7th Workshop on Cognitive Modeling and Computational Linguistics ({CMCL} 2017)",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-0705",
doi = "10.18653/v1/W17-0705",
pages = "35--40",
abstract = "A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doucette-2017-inherent">
<titleInfo>
<title>Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Doucette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2017)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ted</namePart>
<namePart type="family">Gibson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asad</namePart>
<namePart type="family">Sayeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">van Schijndel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Schuler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary.</abstract>
<identifier type="citekey">doucette-2017-inherent</identifier>
<identifier type="doi">10.18653/v1/W17-0705</identifier>
<location>
<url>https://aclanthology.org/W17-0705</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>35</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation
%A Doucette, Amanda
%Y Gibson, Ted
%Y Linzen, Tal
%Y Sayeed, Asad
%Y van Schijndel, Martin
%Y Schuler, William
%S Proceedings of the 7th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2017)
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F doucette-2017-inherent
%X A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary.
%R 10.18653/v1/W17-0705
%U https://aclanthology.org/W17-0705
%U https://doi.org/10.18653/v1/W17-0705
%P 35-40
Markdown (Informal)
[Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation](https://aclanthology.org/W17-0705) (Doucette, CMCL 2017)
ACL