@inproceedings{seeker-kuhn-2014-domain,
title = "An Out-of-Domain Test Suite for Dependency Parsing of {G}erman",
author = "Seeker, Wolfgang and
Kuhn, Jonas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/809_Paper.pdf",
pages = "4066--4073",
abstract = "We present a dependency conversion of five German test sets from five different genres. The dependency representation is made as similar as possible to the dependency representation of TiGer, one of the two big syntactic treebanks of German. The purpose of these test sets is to enable researchers to test dependency parsing models on several different data sets from different text genres. We discuss some easy to compute statistics to demonstrate the variation and differences in the test sets and provide some baseline experiments where we test the effect of additional lexical knowledge on the out-of-domain performance of two state-of-the-art dependency parsers. Finally, we demonstrate with three small experiments that text normalization may be an important step in the standard processing pipeline when applied in an out-of-domain setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seeker-kuhn-2014-domain">
<titleInfo>
<title>An Out-of-Domain Test Suite for Dependency Parsing of German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Seeker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a dependency conversion of five German test sets from five different genres. The dependency representation is made as similar as possible to the dependency representation of TiGer, one of the two big syntactic treebanks of German. The purpose of these test sets is to enable researchers to test dependency parsing models on several different data sets from different text genres. We discuss some easy to compute statistics to demonstrate the variation and differences in the test sets and provide some baseline experiments where we test the effect of additional lexical knowledge on the out-of-domain performance of two state-of-the-art dependency parsers. Finally, we demonstrate with three small experiments that text normalization may be an important step in the standard processing pipeline when applied in an out-of-domain setting.</abstract>
<identifier type="citekey">seeker-kuhn-2014-domain</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/809_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4066</start>
<end>4073</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Out-of-Domain Test Suite for Dependency Parsing of German
%A Seeker, Wolfgang
%A Kuhn, Jonas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F seeker-kuhn-2014-domain
%X We present a dependency conversion of five German test sets from five different genres. The dependency representation is made as similar as possible to the dependency representation of TiGer, one of the two big syntactic treebanks of German. The purpose of these test sets is to enable researchers to test dependency parsing models on several different data sets from different text genres. We discuss some easy to compute statistics to demonstrate the variation and differences in the test sets and provide some baseline experiments where we test the effect of additional lexical knowledge on the out-of-domain performance of two state-of-the-art dependency parsers. Finally, we demonstrate with three small experiments that text normalization may be an important step in the standard processing pipeline when applied in an out-of-domain setting.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/809_Paper.pdf
%P 4066-4073
Markdown (Informal)
[An Out-of-Domain Test Suite for Dependency Parsing of German](http://www.lrec-conf.org/proceedings/lrec2014/pdf/809_Paper.pdf) (Seeker & Kuhn, LREC 2014)
ACL