@inproceedings{costa-jussa-etal-2010-automatic,
title = "Automatic and Human Evaluation Study of a Rule-based and a Statistical {C}atalan-{S}panish Machine Translation Systems",
author = "Costa-juss{\`a}, Marta R. and
Farr{\'u}s, Mireia and
Mari{\~n}o, Jos{\'e} B. and
Fonollosa, Jos{\'e} A. R.",
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/47_Paper.pdf",
abstract = "Machine translation systems can be classified into rule-based and corpus-based approaches, in terms of their core technology. Since both paradigms have largely been used during the last years, one of the aims in the research community is to know how these systems differ in terms of translation quality. To this end, this paper reports a study and comparison of a rule-based and a corpus-based (particularly, statistical) Catalan-Spanish machine translation systems, both of them freely available in the web. The translation quality analysis is performed under two different domains: journalistic and medical. The systems are evaluated by using standard automatic measures, as well as by native human evaluators. Automatic results show that the statistical system performs better than the rule-based system. Human judgements show that in the Spanish-to-Catalan direction the statistical system also performs better than the rule-based system, while in the Catalan-to-Spanish direction is the other way round. Although the statistical system obtains the best automatic scores, its errors tend to be more penalized by human judgements than the errors of the rule-based system. This can be explained because statistical errors are usually unexpected and they do not follow any pattern.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="costa-jussa-etal-2010-automatic">
<titleInfo>
<title>Automatic and Human Evaluation Study of a Rule-based and a Statistical Catalan-Spanish Machine Translation Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mireia</namePart>
<namePart type="family">Farrús</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Mariño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">A</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Fonollosa</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>Machine translation systems can be classified into rule-based and corpus-based approaches, in terms of their core technology. Since both paradigms have largely been used during the last years, one of the aims in the research community is to know how these systems differ in terms of translation quality. To this end, this paper reports a study and comparison of a rule-based and a corpus-based (particularly, statistical) Catalan-Spanish machine translation systems, both of them freely available in the web. The translation quality analysis is performed under two different domains: journalistic and medical. The systems are evaluated by using standard automatic measures, as well as by native human evaluators. Automatic results show that the statistical system performs better than the rule-based system. Human judgements show that in the Spanish-to-Catalan direction the statistical system also performs better than the rule-based system, while in the Catalan-to-Spanish direction is the other way round. Although the statistical system obtains the best automatic scores, its errors tend to be more penalized by human judgements than the errors of the rule-based system. This can be explained because statistical errors are usually unexpected and they do not follow any pattern.</abstract>
<identifier type="citekey">costa-jussa-etal-2010-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/47_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic and Human Evaluation Study of a Rule-based and a Statistical Catalan-Spanish Machine Translation Systems
%A Costa-jussà, Marta R.
%A Farrús, Mireia
%A Mariño, José B.
%A Fonollosa, José A. R.
%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 costa-jussa-etal-2010-automatic
%X Machine translation systems can be classified into rule-based and corpus-based approaches, in terms of their core technology. Since both paradigms have largely been used during the last years, one of the aims in the research community is to know how these systems differ in terms of translation quality. To this end, this paper reports a study and comparison of a rule-based and a corpus-based (particularly, statistical) Catalan-Spanish machine translation systems, both of them freely available in the web. The translation quality analysis is performed under two different domains: journalistic and medical. The systems are evaluated by using standard automatic measures, as well as by native human evaluators. Automatic results show that the statistical system performs better than the rule-based system. Human judgements show that in the Spanish-to-Catalan direction the statistical system also performs better than the rule-based system, while in the Catalan-to-Spanish direction is the other way round. Although the statistical system obtains the best automatic scores, its errors tend to be more penalized by human judgements than the errors of the rule-based system. This can be explained because statistical errors are usually unexpected and they do not follow any pattern.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/47_Paper.pdf
Markdown (Informal)
[Automatic and Human Evaluation Study of a Rule-based and a Statistical Catalan-Spanish Machine Translation Systems](http://www.lrec-conf.org/proceedings/lrec2010/pdf/47_Paper.pdf) (Costa-jussà et al., LREC 2010)
ACL