@inproceedings{trushkina-etal-2008-sentence,
title = "Sentence Alignment in {DPC}: Maximizing Precision, Minimizing Human Effort",
author = "Trushkina, Julia and
Macken, Lieve and
Paulussen, Hans",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/126_paper.pdf",
abstract = "A wide spectrum of multilingual applications have aligned parallel corpora as their prerequisite. The aim of the project described in this paper is to build a multilingual corpus where all sentences are aligned at very high precision with a minimal human effort involved. The experiments on a combination of sentence aligners with different underlying algorithms described in this paper showed that by verifying only those links which were not recognized by at least two aligners, an error rate can be reduced by 93.76{\%} as compared to the performance of the best aligner. Such manual involvement concerned only a small portion of all data (6{\%}). This significantly reduces a load of manual work necessary to achieve nearly 100{\%} accuracy of alignment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trushkina-etal-2008-sentence">
<titleInfo>
<title>Sentence Alignment in DPC: Maximizing Precision, Minimizing Human Effort</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Trushkina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lieve</namePart>
<namePart type="family">Macken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hans</namePart>
<namePart type="family">Paulussen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A wide spectrum of multilingual applications have aligned parallel corpora as their prerequisite. The aim of the project described in this paper is to build a multilingual corpus where all sentences are aligned at very high precision with a minimal human effort involved. The experiments on a combination of sentence aligners with different underlying algorithms described in this paper showed that by verifying only those links which were not recognized by at least two aligners, an error rate can be reduced by 93.76% as compared to the performance of the best aligner. Such manual involvement concerned only a small portion of all data (6%). This significantly reduces a load of manual work necessary to achieve nearly 100% accuracy of alignment.</abstract>
<identifier type="citekey">trushkina-etal-2008-sentence</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/126_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence Alignment in DPC: Maximizing Precision, Minimizing Human Effort
%A Trushkina, Julia
%A Macken, Lieve
%A Paulussen, Hans
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F trushkina-etal-2008-sentence
%X A wide spectrum of multilingual applications have aligned parallel corpora as their prerequisite. The aim of the project described in this paper is to build a multilingual corpus where all sentences are aligned at very high precision with a minimal human effort involved. The experiments on a combination of sentence aligners with different underlying algorithms described in this paper showed that by verifying only those links which were not recognized by at least two aligners, an error rate can be reduced by 93.76% as compared to the performance of the best aligner. Such manual involvement concerned only a small portion of all data (6%). This significantly reduces a load of manual work necessary to achieve nearly 100% accuracy of alignment.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/126_paper.pdf
Markdown (Informal)
[Sentence Alignment in DPC: Maximizing Precision, Minimizing Human Effort](http://www.lrec-conf.org/proceedings/lrec2008/pdf/126_paper.pdf) (Trushkina et al., LREC 2008)
ACL