@inproceedings{pighin-etal-2012-faust,
title = "The {FAUST} Corpus of Adequacy Assessments for Real-World Machine Translation Output",
author = "Pighin, Daniele and
M{\`a}rquez, Llu{\'\i}s and
Formiga, Llu{\'\i}s",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/370_Paper.pdf",
pages = "29--35",
abstract = "We present a corpus consisting of 11,292 real-world English to Spanish automatic translations annotated with relative (ranking) and absolute (adequate/non-adequate) quality assessments. The translation requests, collected through the popular translation portal \url{http://reverso.net}, provide a most variated sample of real-world machine translation (MT) usage, from complete sentences to units of one or two words, from well-formed to hardly intelligible texts, from technical documents to colloquial and slang snippets. In this paper, we present 1) a preliminary annotation experiment that we carried out to select the most appropriate quality criterion to be used for these data, 2) a graph-based methodology inspired by Interactive Genetic Algorithms to reduce the annotation effort, and 3) the outcomes of the full-scale annotation experiment, which result in a valuable and original resource for the analysis and characterization of MT-output quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pighin-etal-2012-faust">
<titleInfo>
<title>The FAUST Corpus of Adequacy Assessments for Real-World Machine Translation Output</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniele</namePart>
<namePart type="family">Pighin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Formiga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a corpus consisting of 11,292 real-world English to Spanish automatic translations annotated with relative (ranking) and absolute (adequate/non-adequate) quality assessments. The translation requests, collected through the popular translation portal http://reverso.net, provide a most variated sample of real-world machine translation (MT) usage, from complete sentences to units of one or two words, from well-formed to hardly intelligible texts, from technical documents to colloquial and slang snippets. In this paper, we present 1) a preliminary annotation experiment that we carried out to select the most appropriate quality criterion to be used for these data, 2) a graph-based methodology inspired by Interactive Genetic Algorithms to reduce the annotation effort, and 3) the outcomes of the full-scale annotation experiment, which result in a valuable and original resource for the analysis and characterization of MT-output quality.</abstract>
<identifier type="citekey">pighin-etal-2012-faust</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/370_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>29</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The FAUST Corpus of Adequacy Assessments for Real-World Machine Translation Output
%A Pighin, Daniele
%A Màrquez, Lluís
%A Formiga, Lluís
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F pighin-etal-2012-faust
%X We present a corpus consisting of 11,292 real-world English to Spanish automatic translations annotated with relative (ranking) and absolute (adequate/non-adequate) quality assessments. The translation requests, collected through the popular translation portal http://reverso.net, provide a most variated sample of real-world machine translation (MT) usage, from complete sentences to units of one or two words, from well-formed to hardly intelligible texts, from technical documents to colloquial and slang snippets. In this paper, we present 1) a preliminary annotation experiment that we carried out to select the most appropriate quality criterion to be used for these data, 2) a graph-based methodology inspired by Interactive Genetic Algorithms to reduce the annotation effort, and 3) the outcomes of the full-scale annotation experiment, which result in a valuable and original resource for the analysis and characterization of MT-output quality.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/370_Paper.pdf
%P 29-35
Markdown (Informal)
[The FAUST Corpus of Adequacy Assessments for Real-World Machine Translation Output](http://www.lrec-conf.org/proceedings/lrec2012/pdf/370_Paper.pdf) (Pighin et al., LREC 2012)
ACL