@inproceedings{dzeroski-etal-2006-towards,
title = "Towards a {S}lovene Dependency Treebank",
author = "D{\v{z}}eroski, Sa{\v{s}}o and
Erjavec, Toma{\v{z}} and
Ledinek, Nina and
Pajas, Petr and
{\v{Z}}abokrtsky, Zdenek and
{\v{Z}}ele, Andreja",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/133_pdf.pdf",
abstract = "The paper presents the initial release of the Slovene Dependency Treebank, currently containing 2000 sentences or 30.000 words. Ourapproach to annotation is based on the Prague Dependency Treebank, which serves as an excellent model due to the similarity of the languages, the existence of a detailed annotation guide and an annotation editor. The initial treebank contains a portion of theMULTEXT-East parallel word-level annotated corpus, namely the firstpart of the Slovene translation of Orwell's 1984. This corpus was first parsed automatically, to arrive at the initial analytic level dependency trees. These were then hand corrected using the tree editorTrEd; simultaneously, the Czech annotation manual was modified forSlovene. The current version is available in XML/TEI, as well asderived formats, and has been used in a comparative evaluation using the MALT parser, and as one of the languages present in the CoNLL-Xshared task on dependency parsing. The paper also discusses further work, in the first instance the composition of the corpus to be annotated next.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dzeroski-etal-2006-towards">
<titleInfo>
<title>Towards a Slovene Dependency Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sašo</namePart>
<namePart type="family">Džeroski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Ledinek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Pajas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdenek</namePart>
<namePart type="family">Žabokrtsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreja</namePart>
<namePart type="family">Žele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper presents the initial release of the Slovene Dependency Treebank, currently containing 2000 sentences or 30.000 words. Ourapproach to annotation is based on the Prague Dependency Treebank, which serves as an excellent model due to the similarity of the languages, the existence of a detailed annotation guide and an annotation editor. The initial treebank contains a portion of theMULTEXT-East parallel word-level annotated corpus, namely the firstpart of the Slovene translation of Orwell’s 1984. This corpus was first parsed automatically, to arrive at the initial analytic level dependency trees. These were then hand corrected using the tree editorTrEd; simultaneously, the Czech annotation manual was modified forSlovene. The current version is available in XML/TEI, as well asderived formats, and has been used in a comparative evaluation using the MALT parser, and as one of the languages present in the CoNLL-Xshared task on dependency parsing. The paper also discusses further work, in the first instance the composition of the corpus to be annotated next.</abstract>
<identifier type="citekey">dzeroski-etal-2006-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/133_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Slovene Dependency Treebank
%A Džeroski, Sašo
%A Erjavec, Tomaž
%A Ledinek, Nina
%A Pajas, Petr
%A Žabokrtsky, Zdenek
%A Žele, Andreja
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F dzeroski-etal-2006-towards
%X The paper presents the initial release of the Slovene Dependency Treebank, currently containing 2000 sentences or 30.000 words. Ourapproach to annotation is based on the Prague Dependency Treebank, which serves as an excellent model due to the similarity of the languages, the existence of a detailed annotation guide and an annotation editor. The initial treebank contains a portion of theMULTEXT-East parallel word-level annotated corpus, namely the firstpart of the Slovene translation of Orwell’s 1984. This corpus was first parsed automatically, to arrive at the initial analytic level dependency trees. These were then hand corrected using the tree editorTrEd; simultaneously, the Czech annotation manual was modified forSlovene. The current version is available in XML/TEI, as well asderived formats, and has been used in a comparative evaluation using the MALT parser, and as one of the languages present in the CoNLL-Xshared task on dependency parsing. The paper also discusses further work, in the first instance the composition of the corpus to be annotated next.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/133_pdf.pdf
Markdown (Informal)
[Towards a Slovene Dependency Treebank](http://www.lrec-conf.org/proceedings/lrec2006/pdf/133_pdf.pdf) (Džeroski et al., LREC 2006)
ACL
- Sašo Džeroski, Tomaž Erjavec, Nina Ledinek, Petr Pajas, Zdenek Žabokrtsky, and Andreja Žele. 2006. Towards a Slovene Dependency Treebank. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).