@inproceedings{megyesi-etal-2008-swedish,
title = "{S}wedish-{T}urkish Parallel Treebank",
author = "Megyesi, Be{\'a}ta and
Dahlqvist, Bengt and
Pettersson, Eva and
Nivre, Joakim",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/121_paper.pdf",
abstract = "In this paper, we describe our work on building a parallel treebank for a less studied and typologically dissimilar language pair, namely Swedish and Turkish. The treebank is a balanced syntactically annotated corpus containing both fiction and technical documents. In total, it consists of approximately 160,000 tokens in Swedish and 145,000 in Turkish. The texts are linguistically annotated using different layers from part of speech tags and morphological features to dependency annotation. Each layer is automatically processed by using basic language resources for the involved languages. The sentences and words are aligned, and partly manually corrected. We create the treebank by reusing and adjusting existing tools for the automatic annotation, alignment, and their correction and visualization. The treebank was developed within the project supporting research environment for minor languages aiming at to create representative language resources for language pairs dissimilar in language structure. Therefore, efforts are put on developing a general method for formatting and annotation procedure, as well as using tools that can be applied to other language pairs easily.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="megyesi-etal-2008-swedish">
<titleInfo>
<title>Swedish-Turkish Parallel Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bengt</namePart>
<namePart type="family">Dahlqvist</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Pettersson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our work on building a parallel treebank for a less studied and typologically dissimilar language pair, namely Swedish and Turkish. The treebank is a balanced syntactically annotated corpus containing both fiction and technical documents. In total, it consists of approximately 160,000 tokens in Swedish and 145,000 in Turkish. The texts are linguistically annotated using different layers from part of speech tags and morphological features to dependency annotation. Each layer is automatically processed by using basic language resources for the involved languages. The sentences and words are aligned, and partly manually corrected. We create the treebank by reusing and adjusting existing tools for the automatic annotation, alignment, and their correction and visualization. The treebank was developed within the project supporting research environment for minor languages aiming at to create representative language resources for language pairs dissimilar in language structure. Therefore, efforts are put on developing a general method for formatting and annotation procedure, as well as using tools that can be applied to other language pairs easily.</abstract>
<identifier type="citekey">megyesi-etal-2008-swedish</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/121_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Swedish-Turkish Parallel Treebank
%A Megyesi, Beáta
%A Dahlqvist, Bengt
%A Pettersson, Eva
%A Nivre, Joakim
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F megyesi-etal-2008-swedish
%X In this paper, we describe our work on building a parallel treebank for a less studied and typologically dissimilar language pair, namely Swedish and Turkish. The treebank is a balanced syntactically annotated corpus containing both fiction and technical documents. In total, it consists of approximately 160,000 tokens in Swedish and 145,000 in Turkish. The texts are linguistically annotated using different layers from part of speech tags and morphological features to dependency annotation. Each layer is automatically processed by using basic language resources for the involved languages. The sentences and words are aligned, and partly manually corrected. We create the treebank by reusing and adjusting existing tools for the automatic annotation, alignment, and their correction and visualization. The treebank was developed within the project supporting research environment for minor languages aiming at to create representative language resources for language pairs dissimilar in language structure. Therefore, efforts are put on developing a general method for formatting and annotation procedure, as well as using tools that can be applied to other language pairs easily.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/121_paper.pdf
Markdown (Informal)
[Swedish-Turkish Parallel Treebank](http://www.lrec-conf.org/proceedings/lrec2008/pdf/121_paper.pdf) (Megyesi et al., LREC 2008)
ACL
- Beáta Megyesi, Bengt Dahlqvist, Eva Pettersson, and Joakim Nivre. 2008. Swedish-Turkish Parallel Treebank. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).