@inproceedings{bojar-etal-2010-evaluating,
title = "Evaluating Utility of Data Sources in a Large Parallel {C}zech-{E}nglish Corpus {C}z{E}ng 0.9",
author = "Bojar, Ond{\v{r}}ej and
Li{\v{s}}ka, Adam and
{\v{Z}}abokrtsk{\'y}, Zden{\v{e}}k",
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/642_Paper.pdf",
abstract = "CzEng 0.9 is the third release of a large parallel corpus of Czech and English. For the current release, CzEng was extended by significant amount of texts from various types of sources, including parallel web pages, electronically available books and subtitles. This paper describes and evaluates filtering techniques employed in the process in order to avoid misaligned or otherwise damaged parallel sentences in the collection. We estimate the precision and recall of two sets of filters. The first set was used to process the data before their inclusion into CzEng. The filters from the second set were newly created to improve the filtering process for future releases of CzEng. Given the overall amount and variance of sources of the data, our experiments illustrate the utility of parallel data sources with respect to extractable parallel segments. As a similar behaviour can be expected for other language pairs, our results can be interpreted as guidelines indicating which sources should other researchers exploit first.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bojar-etal-2010-evaluating">
<titleInfo>
<title>Evaluating Utility of Data Sources in a Large Parallel Czech-English Corpus CzEng 0.9</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Liška</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdeněk</namePart>
<namePart type="family">Žabokrtský</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>CzEng 0.9 is the third release of a large parallel corpus of Czech and English. For the current release, CzEng was extended by significant amount of texts from various types of sources, including parallel web pages, electronically available books and subtitles. This paper describes and evaluates filtering techniques employed in the process in order to avoid misaligned or otherwise damaged parallel sentences in the collection. We estimate the precision and recall of two sets of filters. The first set was used to process the data before their inclusion into CzEng. The filters from the second set were newly created to improve the filtering process for future releases of CzEng. Given the overall amount and variance of sources of the data, our experiments illustrate the utility of parallel data sources with respect to extractable parallel segments. As a similar behaviour can be expected for other language pairs, our results can be interpreted as guidelines indicating which sources should other researchers exploit first.</abstract>
<identifier type="citekey">bojar-etal-2010-evaluating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/642_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Utility of Data Sources in a Large Parallel Czech-English Corpus CzEng 0.9
%A Bojar, Ondřej
%A Liška, Adam
%A Žabokrtský, Zdeněk
%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 bojar-etal-2010-evaluating
%X CzEng 0.9 is the third release of a large parallel corpus of Czech and English. For the current release, CzEng was extended by significant amount of texts from various types of sources, including parallel web pages, electronically available books and subtitles. This paper describes and evaluates filtering techniques employed in the process in order to avoid misaligned or otherwise damaged parallel sentences in the collection. We estimate the precision and recall of two sets of filters. The first set was used to process the data before their inclusion into CzEng. The filters from the second set were newly created to improve the filtering process for future releases of CzEng. Given the overall amount and variance of sources of the data, our experiments illustrate the utility of parallel data sources with respect to extractable parallel segments. As a similar behaviour can be expected for other language pairs, our results can be interpreted as guidelines indicating which sources should other researchers exploit first.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/642_Paper.pdf
Markdown (Informal)
[Evaluating Utility of Data Sources in a Large Parallel Czech-English Corpus CzEng 0.9](http://www.lrec-conf.org/proceedings/lrec2010/pdf/642_Paper.pdf) (Bojar et al., LREC 2010)
ACL