<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gorman-sproat-2016-minimally">
    <titleInfo>
        <title>Minimally Supervised Number Normalization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kyle</namePart>
        <namePart type="family">Gorman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Richard</namePart>
        <namePart type="family">Sproat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016</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 propose two models for verbalizing numbers, a key component in speech recognition and synthesis systems. The first model uses an end-to-end recurrent neural network. The second model, drawing inspiration from the linguistics literature, uses finite-state transducers constructed with a minimal amount of training data. While both models achieve near-perfect performance, the latter model can be trained using several orders of magnitude less data than the former, making it particularly useful for low-resource languages.</abstract>
    <identifier type="citekey">gorman-sproat-2016-minimally</identifier>
    <identifier type="doi">10.1162/tacl_a_00114</identifier>
    <location>
        <url>https://aclanthology.org/Q16-1036</url>
    </location>
    <part>
        <date>2016</date>
        <detail type="volume"><number>4</number></detail>
        <extent unit="page">
            <start>507</start>
            <end>519</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Minimally Supervised Number Normalization
%A Gorman, Kyle
%A Sproat, Richard
%J Transactions of the Association for Computational Linguistics
%D 2016
%V 4
%I MIT Press
%C Cambridge, MA
%F gorman-sproat-2016-minimally
%X We propose two models for verbalizing numbers, a key component in speech recognition and synthesis systems. The first model uses an end-to-end recurrent neural network. The second model, drawing inspiration from the linguistics literature, uses finite-state transducers constructed with a minimal amount of training data. While both models achieve near-perfect performance, the latter model can be trained using several orders of magnitude less data than the former, making it particularly useful for low-resource languages.
%R 10.1162/tacl_a_00114
%U https://aclanthology.org/Q16-1036
%U https://doi.org/10.1162/tacl_a_00114
%P 507-519

Markdown (Informal)

[Minimally Supervised Number Normalization](https://aclanthology.org/Q16-1036) (Gorman & Sproat, TACL 2016)

• Minimally Supervised Number Normalization (Gorman & Sproat, TACL 2016)

ACL

• Kyle Gorman and Richard Sproat. 2016. Minimally Supervised Number Normalization. Transactions of the Association for Computational Linguistics, 4:507–519.