@inproceedings{bojar-prokopova-2006-czech,
title = "{C}zech-{E}nglish Word Alignment",
author = "Bojar, Ond{\v{r}}ej and
Prokopov{\'a}, Magdelena",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/285_pdf.pdf",
abstract = "We describe an experiment with Czech-English word alignment. Half a thousand sentences were manually annotated by two annotators in parallel and the most frequent reasons for disagreement are described. We evaluate the accuracy of GIZA++ alignment toolkit on the data and identify that lemmatization of the Czech part can reduce alignment error to a half. Furthermore we document that about 38{\%} of tokens difficult for GIZA++ were difficult for humans already.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bojar-prokopova-2006-czech">
<titleInfo>
<title>Czech-English Word Alignment</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">Magdelena</namePart>
<namePart type="family">Prokopová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe an experiment with Czech-English word alignment. Half a thousand sentences were manually annotated by two annotators in parallel and the most frequent reasons for disagreement are described. We evaluate the accuracy of GIZA++ alignment toolkit on the data and identify that lemmatization of the Czech part can reduce alignment error to a half. Furthermore we document that about 38% of tokens difficult for GIZA++ were difficult for humans already.</abstract>
<identifier type="citekey">bojar-prokopova-2006-czech</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/285_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Czech-English Word Alignment
%A Bojar, Ondřej
%A Prokopová, Magdelena
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F bojar-prokopova-2006-czech
%X We describe an experiment with Czech-English word alignment. Half a thousand sentences were manually annotated by two annotators in parallel and the most frequent reasons for disagreement are described. We evaluate the accuracy of GIZA++ alignment toolkit on the data and identify that lemmatization of the Czech part can reduce alignment error to a half. Furthermore we document that about 38% of tokens difficult for GIZA++ were difficult for humans already.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/285_pdf.pdf
Markdown (Informal)
[Czech-English Word Alignment](http://www.lrec-conf.org/proceedings/lrec2006/pdf/285_pdf.pdf) (Bojar & Prokopová, LREC 2006)
ACL
- Ondřej Bojar and Magdelena Prokopová. 2006. Czech-English Word Alignment. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).