<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prickett-etal-2018-seq2seq">
    <titleInfo>
        <title>Seq2Seq Models with Dropout can Learn Generalizable Reduplication</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Brandon</namePart>
        <namePart type="family">Prickett</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aaron</namePart>
        <namePart type="family">Traylor</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joe</namePart>
        <namePart type="family">Pater</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sandra</namePart>
            <namePart type="family">Kuebler</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Garrett</namePart>
            <namePart type="family">Nicolai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Natural language reduplication can pose a challenge to neural models of language, and has been argued to require variables (Marcus et al., 1999). Sequence-to-sequence neural networks have been shown to perform well at a number of other morphological tasks (Cotterell et al., 2016), and produce results that highly correlate with human behavior (Kirov, 2017; Kirov &amp; Cotterell, 2018) but do not include any explicit variables in their architecture. We find that they can learn a reduplicative pattern that generalizes to novel segments if they are trained with dropout (Srivastava et al., 2014). We argue that this matches the scope of generalization observed in human reduplication.</abstract>
    <identifier type="citekey">prickett-etal-2018-seq2seq</identifier>
    <identifier type="doi">10.18653/v1/W18-5810</identifier>
    <location>
        <url>https://aclanthology.org/W18-5810</url>
    </location>
    <part>
        <date>2018-10</date>
        <extent unit="page">
            <start>93</start>
            <end>100</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Seq2Seq Models with Dropout can Learn Generalizable Reduplication
%A Prickett, Brandon
%A Traylor, Aaron
%A Pater, Joe
%Y Kuebler, Sandra
%Y Nicolai, Garrett
%S Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F prickett-etal-2018-seq2seq
%X Natural language reduplication can pose a challenge to neural models of language, and has been argued to require variables (Marcus et al., 1999). Sequence-to-sequence neural networks have been shown to perform well at a number of other morphological tasks (Cotterell et al., 2016), and produce results that highly correlate with human behavior (Kirov, 2017; Kirov & Cotterell, 2018) but do not include any explicit variables in their architecture. We find that they can learn a reduplicative pattern that generalizes to novel segments if they are trained with dropout (Srivastava et al., 2014). We argue that this matches the scope of generalization observed in human reduplication.
%R 10.18653/v1/W18-5810
%U https://aclanthology.org/W18-5810
%U https://doi.org/10.18653/v1/W18-5810
%P 93-100

Markdown (Informal)

[Seq2Seq Models with Dropout can Learn Generalizable Reduplication](https://aclanthology.org/W18-5810) (Prickett et al., EMNLP 2018)

• Seq2Seq Models with Dropout can Learn Generalizable Reduplication (Prickett et al., EMNLP 2018)

ACL

• Brandon Prickett, Aaron Traylor, and Joe Pater. 2018. Seq2Seq Models with Dropout can Learn Generalizable Reduplication. In Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 93–100, Brussels, Belgium. Association for Computational Linguistics.