@inproceedings{arias-etal-2014-boosting,
title = "Boosting the creation of a treebank",
author = "Arias, Blanca and
Bel, N{\'u}ria and
Lorente, Merc{\`e} and
Marim{\'o}n, Montserrat and
Mil{\`a}, Alba and
Vivaldi, Jorge and
Padr{\'o}, Muntsa and
Fomicheva, Marina and
Larrea, Imanol",
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/225_Paper.pdf",
pages = "775--781",
abstract = "In this paper we present the results of an ongoing experiment of bootstrapping a Treebank for Catalan by using a Dependency Parser trained with Spanish sentences. In order to save time and cost, our approach was to profit from the typological similarities between Catalan and Spanish to create a first Catalan data set quickly by automatically: (i) annotating with a de-lexicalized Spanish parser, (ii) manually correcting the parses, and (iii) using the Catalan corrected sentences to train a Catalan parser. The results showed that the number of parsed sentences required to train a Catalan parser is about 1000 that were achieved in 4 months, with 2 annotators.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arias-etal-2014-boosting">
<titleInfo>
<title>Boosting the creation of a treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Blanca</namePart>
<namePart type="family">Arias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mercè</namePart>
<namePart type="family">Lorente</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Montserrat</namePart>
<namePart type="family">Marimón</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alba</namePart>
<namePart type="family">Milà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Vivaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muntsa</namePart>
<namePart type="family">Padró</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Fomicheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imanol</namePart>
<namePart type="family">Larrea</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>In this paper we present the results of an ongoing experiment of bootstrapping a Treebank for Catalan by using a Dependency Parser trained with Spanish sentences. In order to save time and cost, our approach was to profit from the typological similarities between Catalan and Spanish to create a first Catalan data set quickly by automatically: (i) annotating with a de-lexicalized Spanish parser, (ii) manually correcting the parses, and (iii) using the Catalan corrected sentences to train a Catalan parser. The results showed that the number of parsed sentences required to train a Catalan parser is about 1000 that were achieved in 4 months, with 2 annotators.</abstract>
<identifier type="citekey">arias-etal-2014-boosting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/225_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>775</start>
<end>781</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Boosting the creation of a treebank
%A Arias, Blanca
%A Bel, Núria
%A Lorente, Mercè
%A Marimón, Montserrat
%A Milà, Alba
%A Vivaldi, Jorge
%A Padró, Muntsa
%A Fomicheva, Marina
%A Larrea, Imanol
%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 arias-etal-2014-boosting
%X In this paper we present the results of an ongoing experiment of bootstrapping a Treebank for Catalan by using a Dependency Parser trained with Spanish sentences. In order to save time and cost, our approach was to profit from the typological similarities between Catalan and Spanish to create a first Catalan data set quickly by automatically: (i) annotating with a de-lexicalized Spanish parser, (ii) manually correcting the parses, and (iii) using the Catalan corrected sentences to train a Catalan parser. The results showed that the number of parsed sentences required to train a Catalan parser is about 1000 that were achieved in 4 months, with 2 annotators.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/225_Paper.pdf
%P 775-781
Markdown (Informal)
[Boosting the creation of a treebank](http://www.lrec-conf.org/proceedings/lrec2014/pdf/225_Paper.pdf) (Arias et al., LREC 2014)
ACL
- Blanca Arias, Núria Bel, Mercè Lorente, Montserrat Marimón, Alba Milà, Jorge Vivaldi, Muntsa Padró, Marina Fomicheva, and Imanol Larrea. 2014. Boosting the creation of a treebank. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 775–781, Reykjavik, Iceland. European Language Resources Association (ELRA).