@inproceedings{megyesi-etal-2010-english,
title = "The {E}nglish-{S}wedish-{T}urkish Parallel Treebank",
author = "Megyesi, Be{\'a}ta and
Dahlqvist, Bengt and
Csat{\'o}, {\'E}va {\'A}. and
Nivre, Joakim",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/116_Paper.pdf",
abstract = "We describe a syntactically annotated parallel corpus containing typologically partly different languages, namely English, Swedish and Turkish. The corpus consists of approximately 300 000 tokens in Swedish, 160 000 in Turkish and 150 000 in English, containing both fiction and technical documents. We build the corpus by using the Uplug toolkit for automatic structural markup, such as tokenization and sentence segmentation, as well as sentence and word alignment. In addition, we use basic language resource kits for the linguistic analysis of the languages involved. The annotation is carried on various layers from morphological and part of speech analysis to dependency structures. The tools used for linguistic annotation, e.g.,{\textbackslash} HunPos tagger and MaltParser, are freely available data-driven resources, trained on existing corpora and treebanks for each language. The parallel treebank is used in teaching and linguistic research to study the relationship between the structurally different languages. In order to study the treebank, several tools have been developed for the visualization of the annotation and alignment, allowing search for linguistic patterns.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="megyesi-etal-2010-english">
<titleInfo>
<title>The English-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">Éva</namePart>
<namePart type="given">Á.</namePart>
<namePart type="family">Csató</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>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe a syntactically annotated parallel corpus containing typologically partly different languages, namely English, Swedish and Turkish. The corpus consists of approximately 300 000 tokens in Swedish, 160 000 in Turkish and 150 000 in English, containing both fiction and technical documents. We build the corpus by using the Uplug toolkit for automatic structural markup, such as tokenization and sentence segmentation, as well as sentence and word alignment. In addition, we use basic language resource kits for the linguistic analysis of the languages involved. The annotation is carried on various layers from morphological and part of speech analysis to dependency structures. The tools used for linguistic annotation, e.g.,\textbackslash HunPos tagger and MaltParser, are freely available data-driven resources, trained on existing corpora and treebanks for each language. The parallel treebank is used in teaching and linguistic research to study the relationship between the structurally different languages. In order to study the treebank, several tools have been developed for the visualization of the annotation and alignment, allowing search for linguistic patterns.</abstract>
<identifier type="citekey">megyesi-etal-2010-english</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/116_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The English-Swedish-Turkish Parallel Treebank
%A Megyesi, Beáta
%A Dahlqvist, Bengt
%A Csató, Éva Á.
%A Nivre, Joakim
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F megyesi-etal-2010-english
%X We describe a syntactically annotated parallel corpus containing typologically partly different languages, namely English, Swedish and Turkish. The corpus consists of approximately 300 000 tokens in Swedish, 160 000 in Turkish and 150 000 in English, containing both fiction and technical documents. We build the corpus by using the Uplug toolkit for automatic structural markup, such as tokenization and sentence segmentation, as well as sentence and word alignment. In addition, we use basic language resource kits for the linguistic analysis of the languages involved. The annotation is carried on various layers from morphological and part of speech analysis to dependency structures. The tools used for linguistic annotation, e.g.,\textbackslash HunPos tagger and MaltParser, are freely available data-driven resources, trained on existing corpora and treebanks for each language. The parallel treebank is used in teaching and linguistic research to study the relationship between the structurally different languages. In order to study the treebank, several tools have been developed for the visualization of the annotation and alignment, allowing search for linguistic patterns.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/116_Paper.pdf
Markdown (Informal)
[The English-Swedish-Turkish Parallel Treebank](http://www.lrec-conf.org/proceedings/lrec2010/pdf/116_Paper.pdf) (Megyesi et al., LREC 2010)
ACL
- Beáta Megyesi, Bengt Dahlqvist, Éva Á. Csató, and Joakim Nivre. 2010. The English-Swedish-Turkish Parallel Treebank. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).