<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2017-unsupervised">
    <titleInfo>
        <title>Unsupervised Learning of Morphological Forests</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiaming</namePart>
        <namePart type="family">Luo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karthik</namePart>
        <namePart type="family">Narasimhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Regina</namePart>
        <namePart type="family">Barzilay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017</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>This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families, and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.</abstract>
    <identifier type="citekey">luo-etal-2017-unsupervised</identifier>
    <identifier type="doi">10.1162/tacl_a_00066</identifier>
    <location>
        <url>https://aclanthology.org/Q17-1025/</url>
    </location>
    <part>
        <date>2017</date>
        <detail type="volume"><number>5</number></detail>
        <extent unit="page">
            <start>353</start>
            <end>364</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Unsupervised Learning of Morphological Forests
%A Luo, Jiaming
%A Narasimhan, Karthik
%A Barzilay, Regina
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F luo-etal-2017-unsupervised
%X This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families, and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.
%R 10.1162/tacl_a_00066
%U https://aclanthology.org/Q17-1025/
%U https://doi.org/10.1162/tacl_a_00066
%P 353-364

Markdown (Informal)

[Unsupervised Learning of Morphological Forests](https://aclanthology.org/Q17-1025/) (Luo et al., TACL 2017)

• Unsupervised Learning of Morphological Forests (Luo et al., TACL 2017)

ACL

• Jiaming Luo, Karthik Narasimhan, and Regina Barzilay. 2017. Unsupervised Learning of Morphological Forests. Transactions of the Association for Computational Linguistics, 5:353–364.