<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lan-etal-2022-minimum">
    <titleInfo>
        <title>Minimum Description Length Recurrent Neural Networks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nur</namePart>
        <namePart type="family">Lan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michal</namePart>
        <namePart type="family">Geyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emmanuel</namePart>
        <namePart type="family">Chemla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roni</namePart>
        <namePart type="family">Katzir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022</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 train neural networks to optimize a Minimum Description Length score, that is, to balance between the complexity of the network and its accuracy at a task. We show that networks optimizing this objective function master tasks involving memory challenges and go beyond context-free languages. These learners master languages such as anbn, anbncn, anb2n, anbmcn +m, and they perform addition. Moreover, they often do so with 100% accuracy. The networks are small, and their inner workings are transparent. We thus provide formal proofs that their perfect accuracy holds not only on a given test set, but for any input sequence. To our knowledge, no other connectionist model has been shown to capture the underlying grammars for these languages in full generality.</abstract>
    <identifier type="citekey">lan-etal-2022-minimum</identifier>
    <identifier type="doi">10.1162/tacl_a_00489</identifier>
    <location>
        <url>https://aclanthology.org/2022.tacl-1.45</url>
    </location>
    <part>
        <date>2022</date>
        <detail type="volume"><number>10</number></detail>
        <extent unit="page">
            <start>785</start>
            <end>799</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Minimum Description Length Recurrent Neural Networks
%A Lan, Nur
%A Geyer, Michal
%A Chemla, Emmanuel
%A Katzir, Roni
%J Transactions of the Association for Computational Linguistics
%D 2022
%V 10
%I MIT Press
%C Cambridge, MA
%F lan-etal-2022-minimum
%X We train neural networks to optimize a Minimum Description Length score, that is, to balance between the complexity of the network and its accuracy at a task. We show that networks optimizing this objective function master tasks involving memory challenges and go beyond context-free languages. These learners master languages such as anbn, anbncn, anb2n, anbmcn +m, and they perform addition. Moreover, they often do so with 100% accuracy. The networks are small, and their inner workings are transparent. We thus provide formal proofs that their perfect accuracy holds not only on a given test set, but for any input sequence. To our knowledge, no other connectionist model has been shown to capture the underlying grammars for these languages in full generality.
%R 10.1162/tacl_a_00489
%U https://aclanthology.org/2022.tacl-1.45
%U https://doi.org/10.1162/tacl_a_00489
%P 785-799

Markdown (Informal)

[Minimum Description Length Recurrent Neural Networks](https://aclanthology.org/2022.tacl-1.45) (Lan et al., TACL 2022)

• Minimum Description Length Recurrent Neural Networks (Lan et al., TACL 2022)

ACL

• Nur Lan, Michal Geyer, Emmanuel Chemla, and Roni Katzir. 2022. Minimum Description Length Recurrent Neural Networks. Transactions of the Association for Computational Linguistics, 10:785–799.