@inproceedings{seeker-kuhn-2012-making,
title = "Making Ellipses Explicit in Dependency Conversion for a {G}erman Treebank",
author = "Seeker, Wolfgang and
Kuhn, Jonas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/235_Paper.pdf",
pages = "3132--3139",
abstract = "We present a carefully designed dependency conversion of the German phrase-structure treebank TiGer that explicitly represents verb ellipses by introducing empty nodes into the tree. Although the conversion process uses heuristics like many other conversion tools we designed them to fail if no reasonable solution can be found. The failing of the conversion process makes it possible to detect elliptical constructions where the head is missing, but it also allows us to find errors in the original annotation. We discuss the conversion process and the heuristics, and describe some design decisions and error corrections that we applied to the corpus. Since most of today's data-driven dependency parsers are not able to handle empty nodes directly during parsing, our conversion tool also derives a canonical dependency format without empty nodes. It is shown experimentally to be well suited for training statistical dependency parsers by comparing the performance of two parsers from different parsing paradigms on the data set of the CoNLL 2009 Shared Task data and our corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seeker-kuhn-2012-making">
<titleInfo>
<title>Making Ellipses Explicit in Dependency Conversion for a German Treebank</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>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a carefully designed dependency conversion of the German phrase-structure treebank TiGer that explicitly represents verb ellipses by introducing empty nodes into the tree. Although the conversion process uses heuristics like many other conversion tools we designed them to fail if no reasonable solution can be found. The failing of the conversion process makes it possible to detect elliptical constructions where the head is missing, but it also allows us to find errors in the original annotation. We discuss the conversion process and the heuristics, and describe some design decisions and error corrections that we applied to the corpus. Since most of today’s data-driven dependency parsers are not able to handle empty nodes directly during parsing, our conversion tool also derives a canonical dependency format without empty nodes. It is shown experimentally to be well suited for training statistical dependency parsers by comparing the performance of two parsers from different parsing paradigms on the data set of the CoNLL 2009 Shared Task data and our corpus.</abstract>
<identifier type="citekey">seeker-kuhn-2012-making</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/235_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3132</start>
<end>3139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Ellipses Explicit in Dependency Conversion for a German Treebank
%A Seeker, Wolfgang
%A Kuhn, Jonas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F seeker-kuhn-2012-making
%X We present a carefully designed dependency conversion of the German phrase-structure treebank TiGer that explicitly represents verb ellipses by introducing empty nodes into the tree. Although the conversion process uses heuristics like many other conversion tools we designed them to fail if no reasonable solution can be found. The failing of the conversion process makes it possible to detect elliptical constructions where the head is missing, but it also allows us to find errors in the original annotation. We discuss the conversion process and the heuristics, and describe some design decisions and error corrections that we applied to the corpus. Since most of today’s data-driven dependency parsers are not able to handle empty nodes directly during parsing, our conversion tool also derives a canonical dependency format without empty nodes. It is shown experimentally to be well suited for training statistical dependency parsers by comparing the performance of two parsers from different parsing paradigms on the data set of the CoNLL 2009 Shared Task data and our corpus.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/235_Paper.pdf
%P 3132-3139
Markdown (Informal)
[Making Ellipses Explicit in Dependency Conversion for a German Treebank](http://www.lrec-conf.org/proceedings/lrec2012/pdf/235_Paper.pdf) (Seeker & Kuhn, LREC 2012)
ACL