@inproceedings{seljan-etal-2012-bleu,
title = "{BLEU} Evaluation of Machine-Translated {E}nglish-{C}roatian Legislation",
author = "Seljan, Sanja and
Brki{\'c}, Marija and
Vi{\v{c}}i{\'c}, Tomislav",
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/233_Paper.pdf",
pages = "2143--2148",
abstract = "This paper presents work on the evaluation of online available machine translation (MT) service, i.e. Google Translate, for English-Croatian language pair in the domain of legislation. The total set of 200 sentences, for which three reference translations are provided, is divided into short and long sentences. Human evaluation is performed by native speakers, using the criteria of adequacy and fluency. For measuring the reliability of agreement among raters, Fleiss' kappa metric is used. Human evaluation is enriched by error analysis, in order to examine the influence of error types on fluency and adequacy, and to use it in further research. Translation errors are divided into several categories: non-translated words, word omissions, unnecessarily translated words, morphological errors, lexical errors, syntactic errors and incorrect punctuation. The automatic evaluation metric BLEU is calculated with regard to a single and multiple reference translations. System level Pearson's correlation between BLEU scores based on a single and multiple reference translations is given, as well as correlation between short and long sentences BLEU scores, and correlation between the criteria of fluency and adequacy and each error category.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seljan-etal-2012-bleu">
<titleInfo>
<title>BLEU Evaluation of Machine-Translated English-Croatian Legislation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Seljan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marija</namePart>
<namePart type="family">Brkić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomislav</namePart>
<namePart type="family">Vičić</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>This paper presents work on the evaluation of online available machine translation (MT) service, i.e. Google Translate, for English-Croatian language pair in the domain of legislation. The total set of 200 sentences, for which three reference translations are provided, is divided into short and long sentences. Human evaluation is performed by native speakers, using the criteria of adequacy and fluency. For measuring the reliability of agreement among raters, Fleiss’ kappa metric is used. Human evaluation is enriched by error analysis, in order to examine the influence of error types on fluency and adequacy, and to use it in further research. Translation errors are divided into several categories: non-translated words, word omissions, unnecessarily translated words, morphological errors, lexical errors, syntactic errors and incorrect punctuation. The automatic evaluation metric BLEU is calculated with regard to a single and multiple reference translations. System level Pearson’s correlation between BLEU scores based on a single and multiple reference translations is given, as well as correlation between short and long sentences BLEU scores, and correlation between the criteria of fluency and adequacy and each error category.</abstract>
<identifier type="citekey">seljan-etal-2012-bleu</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/233_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2143</start>
<end>2148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BLEU Evaluation of Machine-Translated English-Croatian Legislation
%A Seljan, Sanja
%A Brkić, Marija
%A Vičić, Tomislav
%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 seljan-etal-2012-bleu
%X This paper presents work on the evaluation of online available machine translation (MT) service, i.e. Google Translate, for English-Croatian language pair in the domain of legislation. The total set of 200 sentences, for which three reference translations are provided, is divided into short and long sentences. Human evaluation is performed by native speakers, using the criteria of adequacy and fluency. For measuring the reliability of agreement among raters, Fleiss’ kappa metric is used. Human evaluation is enriched by error analysis, in order to examine the influence of error types on fluency and adequacy, and to use it in further research. Translation errors are divided into several categories: non-translated words, word omissions, unnecessarily translated words, morphological errors, lexical errors, syntactic errors and incorrect punctuation. The automatic evaluation metric BLEU is calculated with regard to a single and multiple reference translations. System level Pearson’s correlation between BLEU scores based on a single and multiple reference translations is given, as well as correlation between short and long sentences BLEU scores, and correlation between the criteria of fluency and adequacy and each error category.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/233_Paper.pdf
%P 2143-2148
Markdown (Informal)
[BLEU Evaluation of Machine-Translated English-Croatian Legislation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/233_Paper.pdf) (Seljan et al., LREC 2012)
ACL