<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="proisl-uhrig-2016-somajo">
    <titleInfo>
        <title>SoMaJo: State-of-the-art tokenization for German web and social media texts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Proisl</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peter</namePart>
        <namePart type="family">Uhrig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 10th Web as Corpus Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Paul</namePart>
            <namePart type="family">Cook</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stefan</namePart>
            <namePart type="family">Evert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Roland</namePart>
            <namePart type="family">Schäfer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Egon</namePart>
            <namePart type="family">Stemle</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Berlin</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <identifier type="citekey">proisl-uhrig-2016-somajo</identifier>
    <identifier type="doi">10.18653/v1/W16-2607</identifier>
    <location>
        <url>https://aclanthology.org/W16-2607</url>
    </location>
    <part>
        <date>2016-08</date>
        <extent unit="page">
            <start>57</start>
            <end>62</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SoMaJo: State-of-the-art tokenization for German web and social media texts
%A Proisl, Thomas
%A Uhrig, Peter
%Y Cook, Paul
%Y Evert, Stefan
%Y Schäfer, Roland
%Y Stemle, Egon
%S Proceedings of the 10th Web as Corpus Workshop
%D 2016
%8 August
%I Association for Computational Linguistics
%C Berlin
%F proisl-uhrig-2016-somajo
%R 10.18653/v1/W16-2607
%U https://aclanthology.org/W16-2607
%U https://doi.org/10.18653/v1/W16-2607
%P 57-62

Markdown (Informal)

[SoMaJo: State-of-the-art tokenization for German web and social media texts](https://aclanthology.org/W16-2607) (Proisl & Uhrig, WAC 2016)

• SoMaJo: State-of-the-art tokenization for German web and social media texts (Proisl & Uhrig, WAC 2016)

ACL

• Thomas Proisl and Peter Uhrig. 2016. SoMaJo: State-of-the-art tokenization for German web and social media texts. In Proceedings of the 10th Web as Corpus Workshop, pages 57–62, Berlin. Association for Computational Linguistics.