@inproceedings{seretan-etal-2014-large,
title = "A Large-Scale Evaluation of Pre-editing Strategies for Improving User-Generated Content Translation",
author = "Seretan, Violeta and
Bouillon, Pierrette and
Gerlach, Johanna",
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/676_Paper.pdf",
pages = "1793--1799",
abstract = "The user-generated content represents an increasing share of the information available today. To make this type of content instantly accessible in another language, the ACCEPT project focuses on developing pre-editing technologies for correcting the source text in order to increase its translatability. Linguistically-informed pre-editing rules have been developed for English and French for the two domains considered by the project, namely, the technical domain and the healthcare domain. In this paper, we present the evaluation experiments carried out to assess the impact of the proposed pre-editing rules on translation quality. Results from a large-scale evaluation campaign show that pre-editing helps indeed attain a better translation quality for a high proportion of the data, the difference with the number of cases where the adverse effect is observed being statistically significant. The ACCEPT pre-editing technology is freely available online and can be used in any Web-based environment to enhance the translatability of user-generated content so that it reaches a broader audience.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seretan-etal-2014-large">
<titleInfo>
<title>A Large-Scale Evaluation of Pre-editing Strategies for Improving User-Generated Content Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Violeta</namePart>
<namePart type="family">Seretan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierrette</namePart>
<namePart type="family">Bouillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Gerlach</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>The user-generated content represents an increasing share of the information available today. To make this type of content instantly accessible in another language, the ACCEPT project focuses on developing pre-editing technologies for correcting the source text in order to increase its translatability. Linguistically-informed pre-editing rules have been developed for English and French for the two domains considered by the project, namely, the technical domain and the healthcare domain. In this paper, we present the evaluation experiments carried out to assess the impact of the proposed pre-editing rules on translation quality. Results from a large-scale evaluation campaign show that pre-editing helps indeed attain a better translation quality for a high proportion of the data, the difference with the number of cases where the adverse effect is observed being statistically significant. The ACCEPT pre-editing technology is freely available online and can be used in any Web-based environment to enhance the translatability of user-generated content so that it reaches a broader audience.</abstract>
<identifier type="citekey">seretan-etal-2014-large</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/676_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1793</start>
<end>1799</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-Scale Evaluation of Pre-editing Strategies for Improving User-Generated Content Translation
%A Seretan, Violeta
%A Bouillon, Pierrette
%A Gerlach, Johanna
%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 seretan-etal-2014-large
%X The user-generated content represents an increasing share of the information available today. To make this type of content instantly accessible in another language, the ACCEPT project focuses on developing pre-editing technologies for correcting the source text in order to increase its translatability. Linguistically-informed pre-editing rules have been developed for English and French for the two domains considered by the project, namely, the technical domain and the healthcare domain. In this paper, we present the evaluation experiments carried out to assess the impact of the proposed pre-editing rules on translation quality. Results from a large-scale evaluation campaign show that pre-editing helps indeed attain a better translation quality for a high proportion of the data, the difference with the number of cases where the adverse effect is observed being statistically significant. The ACCEPT pre-editing technology is freely available online and can be used in any Web-based environment to enhance the translatability of user-generated content so that it reaches a broader audience.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/676_Paper.pdf
%P 1793-1799
Markdown (Informal)
[A Large-Scale Evaluation of Pre-editing Strategies for Improving User-Generated Content Translation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/676_Paper.pdf) (Seretan et al., LREC 2014)
ACL