@inproceedings{costa-etal-2014-translation,
title = "Translation errors from {E}nglish to {P}ortuguese: an annotated corpus",
author = "Costa, Angela and
Lu{\'\i}s, Tiago and
Coheur, Lu{\'\i}sa",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/199_Paper.pdf",
pages = "1231--1234",
abstract = "Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC collection of factoid questions. We have automatically translated these sentences from English into Portuguese using Google Translate and Moses. After we have analysed the errors and created the error annotation taxonomy, the corpus was annotated by a linguist native speaker of Portuguese. Although Google{'}s overall performance was better in the translation task (we have also calculated the BLUE and NIST scores), there are some error types that Moses was better at coping with, specially discourse level errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="costa-etal-2014-translation">
<titleInfo>
<title>Translation errors from English to Portuguese: an annotated corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiago</namePart>
<namePart type="family">Luís</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luísa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC collection of factoid questions. We have automatically translated these sentences from English into Portuguese using Google Translate and Moses. After we have analysed the errors and created the error annotation taxonomy, the corpus was annotated by a linguist native speaker of Portuguese. Although Google’s overall performance was better in the translation task (we have also calculated the BLUE and NIST scores), there are some error types that Moses was better at coping with, specially discourse level errors.</abstract>
<identifier type="citekey">costa-etal-2014-translation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/199_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1231</start>
<end>1234</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation errors from English to Portuguese: an annotated corpus
%A Costa, Angela
%A Luís, Tiago
%A Coheur, Luísa
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F costa-etal-2014-translation
%X Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC collection of factoid questions. We have automatically translated these sentences from English into Portuguese using Google Translate and Moses. After we have analysed the errors and created the error annotation taxonomy, the corpus was annotated by a linguist native speaker of Portuguese. Although Google’s overall performance was better in the translation task (we have also calculated the BLUE and NIST scores), there are some error types that Moses was better at coping with, specially discourse level errors.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/199_Paper.pdf
%P 1231-1234
Markdown (Informal)
[Translation errors from English to Portuguese: an annotated corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/199_Paper.pdf) (Costa et al., LREC 2014)
ACL