@inproceedings{etchegoyhen-etal-2014-machine,
title = "Machine Translation for Subtitling: A Large-Scale Evaluation",
author = "Etchegoyhen, Thierry and
Bywood, Lindsay and
Fishel, Mark and
Georgakopoulou, Panayota and
Jiang, Jie and
van Loenhout, Gerard and
del Pozo, Arantza and
Mau{\v{c}}ec, Mirjam Sepesy and
Turner, Anja and
Volk, Martin",
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/463_Paper.pdf",
pages = "46--53",
abstract = "This article describes a large-scale evaluation of the use of Statistical Machine Translation for professional subtitling. The work was carried out within the FP7 EU-funded project SUMAT and involved two rounds of evaluation: a quality evaluation and a measure of productivity gain/loss. We present the SMT systems built for the project and the corpora they were trained on, which combine professionally created and crowd-sourced data. Evaluation goals, methodology and results are presented for the eleven translation pairs that were evaluated by professional subtitlers. Overall, a majority of the machine translated subtitles received good quality ratings. The results were also positive in terms of productivity, with a global gain approaching 40{\%}. We also evaluated the impact of applying quality estimation and filtering of poor MT output, which resulted in higher productivity gains for filtered files as opposed to fully machine-translated files. Finally, we present and discuss feedback from the subtitlers who participated in the evaluation, a key aspect for any eventual adoption of machine translation technology in professional subtitling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="etchegoyhen-etal-2014-machine">
<titleInfo>
<title>Machine Translation for Subtitling: A Large-Scale Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lindsay</namePart>
<namePart type="family">Bywood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Panayota</namePart>
<namePart type="family">Georgakopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerard</namePart>
<namePart type="family">van Loenhout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arantza</namePart>
<namePart type="family">del Pozo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirjam</namePart>
<namePart type="given">Sepesy</namePart>
<namePart type="family">Maučec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anja</namePart>
<namePart type="family">Turner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Volk</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>This article describes a large-scale evaluation of the use of Statistical Machine Translation for professional subtitling. The work was carried out within the FP7 EU-funded project SUMAT and involved two rounds of evaluation: a quality evaluation and a measure of productivity gain/loss. We present the SMT systems built for the project and the corpora they were trained on, which combine professionally created and crowd-sourced data. Evaluation goals, methodology and results are presented for the eleven translation pairs that were evaluated by professional subtitlers. Overall, a majority of the machine translated subtitles received good quality ratings. The results were also positive in terms of productivity, with a global gain approaching 40%. We also evaluated the impact of applying quality estimation and filtering of poor MT output, which resulted in higher productivity gains for filtered files as opposed to fully machine-translated files. Finally, we present and discuss feedback from the subtitlers who participated in the evaluation, a key aspect for any eventual adoption of machine translation technology in professional subtitling.</abstract>
<identifier type="citekey">etchegoyhen-etal-2014-machine</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/463_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>46</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation for Subtitling: A Large-Scale Evaluation
%A Etchegoyhen, Thierry
%A Bywood, Lindsay
%A Fishel, Mark
%A Georgakopoulou, Panayota
%A Jiang, Jie
%A van Loenhout, Gerard
%A del Pozo, Arantza
%A Maučec, Mirjam Sepesy
%A Turner, Anja
%A Volk, Martin
%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 etchegoyhen-etal-2014-machine
%X This article describes a large-scale evaluation of the use of Statistical Machine Translation for professional subtitling. The work was carried out within the FP7 EU-funded project SUMAT and involved two rounds of evaluation: a quality evaluation and a measure of productivity gain/loss. We present the SMT systems built for the project and the corpora they were trained on, which combine professionally created and crowd-sourced data. Evaluation goals, methodology and results are presented for the eleven translation pairs that were evaluated by professional subtitlers. Overall, a majority of the machine translated subtitles received good quality ratings. The results were also positive in terms of productivity, with a global gain approaching 40%. We also evaluated the impact of applying quality estimation and filtering of poor MT output, which resulted in higher productivity gains for filtered files as opposed to fully machine-translated files. Finally, we present and discuss feedback from the subtitlers who participated in the evaluation, a key aspect for any eventual adoption of machine translation technology in professional subtitling.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/463_Paper.pdf
%P 46-53
Markdown (Informal)
[Machine Translation for Subtitling: A Large-Scale Evaluation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/463_Paper.pdf) (Etchegoyhen et al., LREC 2014)
ACL
- Thierry Etchegoyhen, Lindsay Bywood, Mark Fishel, Panayota Georgakopoulou, Jie Jiang, Gerard van Loenhout, Arantza del Pozo, Mirjam Sepesy Maučec, Anja Turner, and Martin Volk. 2014. Machine Translation for Subtitling: A Large-Scale Evaluation. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 46–53, Reykjavik, Iceland. European Language Resources Association (ELRA).