@inproceedings{seljan-etal-2010-corpus,
title = "Corpus Aligner ({C}or{A}l) Evaluation on {E}nglish-{C}roatian Parallel Corpora",
author = "Seljan, Sanja and
Tadi{\'c}, Marko and
Agi{\'c}, {\v{Z}}eljko and
{\v{S}}najder, Jan and
Ba{\v{s}}i{\'c}, Bojana Dalbelo and
Osmann, Vjekoslav",
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/599_Paper.pdf",
abstract = "An increasing demand for new language resources of recent EU members and accessing countries has in turn initiated the development of different language tools and resources, such as alignment tools and corresponding translation memories for new languages pairs. The primary goal of this paper is to provide a description of a free sentence alignment tool CorAl (Corpus Aligner), developed at the Faculty of Electrical Engineering and Computing, University of Zagreb. The tool performs paragraph alignment at the first step of the alignment process, which is followed by sentence alignment. Description of the tool is followed by its evaluation. The paper describes an experiment with applying the CorAl aligner to a English-Croatian parallel corpus of legislative domain using metrics of precision, recall and F1-measure. Results are discussed and the concluding sections discuss future directions of CorAl development.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seljan-etal-2010-corpus">
<titleInfo>
<title>Corpus Aligner (CorAl) Evaluation on English-Croatian Parallel Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Seljan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Tadić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Željko</namePart>
<namePart type="family">Agić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojana</namePart>
<namePart type="given">Dalbelo</namePart>
<namePart type="family">Bašić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vjekoslav</namePart>
<namePart type="family">Osmann</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>An increasing demand for new language resources of recent EU members and accessing countries has in turn initiated the development of different language tools and resources, such as alignment tools and corresponding translation memories for new languages pairs. The primary goal of this paper is to provide a description of a free sentence alignment tool CorAl (Corpus Aligner), developed at the Faculty of Electrical Engineering and Computing, University of Zagreb. The tool performs paragraph alignment at the first step of the alignment process, which is followed by sentence alignment. Description of the tool is followed by its evaluation. The paper describes an experiment with applying the CorAl aligner to a English-Croatian parallel corpus of legislative domain using metrics of precision, recall and F1-measure. Results are discussed and the concluding sections discuss future directions of CorAl development.</abstract>
<identifier type="citekey">seljan-etal-2010-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/599_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Aligner (CorAl) Evaluation on English-Croatian Parallel Corpora
%A Seljan, Sanja
%A Tadić, Marko
%A Agić, Željko
%A Šnajder, Jan
%A Bašić, Bojana Dalbelo
%A Osmann, Vjekoslav
%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 seljan-etal-2010-corpus
%X An increasing demand for new language resources of recent EU members and accessing countries has in turn initiated the development of different language tools and resources, such as alignment tools and corresponding translation memories for new languages pairs. The primary goal of this paper is to provide a description of a free sentence alignment tool CorAl (Corpus Aligner), developed at the Faculty of Electrical Engineering and Computing, University of Zagreb. The tool performs paragraph alignment at the first step of the alignment process, which is followed by sentence alignment. Description of the tool is followed by its evaluation. The paper describes an experiment with applying the CorAl aligner to a English-Croatian parallel corpus of legislative domain using metrics of precision, recall and F1-measure. Results are discussed and the concluding sections discuss future directions of CorAl development.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/599_Paper.pdf
Markdown (Informal)
[Corpus Aligner (CorAl) Evaluation on English-Croatian Parallel Corpora](http://www.lrec-conf.org/proceedings/lrec2010/pdf/599_Paper.pdf) (Seljan et al., LREC 2010)
ACL