@inproceedings{ozdowska-2008-cross,
title = "Cross-Corpus Evaluation of Word Alignment",
author = "Ozdowska, Sylwia",
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/207_paper.pdf",
abstract = "We present the procedures we implemented to carry out system oriented evaluation of a syntax-based word aligner, ALIBI. While cross-corpus evaluation is still relatively rare in NLP, we take the approach of regarding cross-corpus evaluation as part of system oriented evaluation. Our hypothesis is that the granularity of alignments and the level of syntactic correspondence depend on corpus type; our objective is to assess how this impacts on alignment quality. We test our system on three English-French parallel corpora. The evaluation procedures are defined in accordance with state-of-the-art word alignment evaluation principles. They include, for each corpus, the creation of a reference set containing multiple annotations of the same data, the assessment of inter-annotator agreement rates and an analysis of the reference set obtained. We show that alignment performance varies across corpora according to the multiple reference annotations produced and further motivate our choice of preserving all reference annotations without solving disagreements between annotators.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ozdowska-2008-cross">
<titleInfo>
<title>Cross-Corpus Evaluation of Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sylwia</namePart>
<namePart type="family">Ozdowska</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>We present the procedures we implemented to carry out system oriented evaluation of a syntax-based word aligner, ALIBI. While cross-corpus evaluation is still relatively rare in NLP, we take the approach of regarding cross-corpus evaluation as part of system oriented evaluation. Our hypothesis is that the granularity of alignments and the level of syntactic correspondence depend on corpus type; our objective is to assess how this impacts on alignment quality. We test our system on three English-French parallel corpora. The evaluation procedures are defined in accordance with state-of-the-art word alignment evaluation principles. They include, for each corpus, the creation of a reference set containing multiple annotations of the same data, the assessment of inter-annotator agreement rates and an analysis of the reference set obtained. We show that alignment performance varies across corpora according to the multiple reference annotations produced and further motivate our choice of preserving all reference annotations without solving disagreements between annotators.</abstract>
<identifier type="citekey">ozdowska-2008-cross</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/207_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Corpus Evaluation of Word Alignment
%A Ozdowska, Sylwia
%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 ozdowska-2008-cross
%X We present the procedures we implemented to carry out system oriented evaluation of a syntax-based word aligner, ALIBI. While cross-corpus evaluation is still relatively rare in NLP, we take the approach of regarding cross-corpus evaluation as part of system oriented evaluation. Our hypothesis is that the granularity of alignments and the level of syntactic correspondence depend on corpus type; our objective is to assess how this impacts on alignment quality. We test our system on three English-French parallel corpora. The evaluation procedures are defined in accordance with state-of-the-art word alignment evaluation principles. They include, for each corpus, the creation of a reference set containing multiple annotations of the same data, the assessment of inter-annotator agreement rates and an analysis of the reference set obtained. We show that alignment performance varies across corpora according to the multiple reference annotations produced and further motivate our choice of preserving all reference annotations without solving disagreements between annotators.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/207_paper.pdf
Markdown (Informal)
[Cross-Corpus Evaluation of Word Alignment](http://www.lrec-conf.org/proceedings/lrec2008/pdf/207_paper.pdf) (Ozdowska, LREC 2008)
ACL
- Sylwia Ozdowska. 2008. Cross-Corpus Evaluation of Word Alignment. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).