<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berend-2017-sparse">
    <titleInfo>
        <title>Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gábor</namePart>
        <namePart type="family">Berend</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>In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations. The proposed model obtains (near) state-of-the art performance for both part-of-speech tagging and named entity recognition for a variety of languages. Our model relies only on a few thousand sparse coding-derived features, without applying any modification of the word representations employed for the different tasks. The proposed model has favorable generalization properties as it retains over 89.8% of its average POS tagging accuracy when trained at 1.2% of the total available training data, i.e. 150 sentences per language.</abstract>
    <identifier type="citekey">berend-2017-sparse</identifier>
    <identifier type="doi">10.1162/tacl_a_00059</identifier>
    <location>
        <url>https://aclanthology.org/Q17-1018</url>
    </location>
    <part>
        <date>2017</date>
        <detail type="volume"><number>5</number></detail>
        <extent unit="page">
            <start>247</start>
            <end>261</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling
%A Berend, Gábor
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F berend-2017-sparse
%X In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations. The proposed model obtains (near) state-of-the art performance for both part-of-speech tagging and named entity recognition for a variety of languages. Our model relies only on a few thousand sparse coding-derived features, without applying any modification of the word representations employed for the different tasks. The proposed model has favorable generalization properties as it retains over 89.8% of its average POS tagging accuracy when trained at 1.2% of the total available training data, i.e. 150 sentences per language.
%R 10.1162/tacl_a_00059
%U https://aclanthology.org/Q17-1018
%U https://doi.org/10.1162/tacl_a_00059
%P 247-261

Markdown (Informal)

[Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling](https://aclanthology.org/Q17-1018) (Berend, TACL 2017)

• Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling (Berend, TACL 2017)

ACL

• Gábor Berend. 2017. Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling. Transactions of the Association for Computational Linguistics, 5:247–261.