@inproceedings{logacheva-specia-2014-quality,
title = "A Quality-based Active Sample Selection Strategy for Statistical Machine Translation",
author = "Logacheva, Varvara and
Specia, Lucia",
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/658_Paper.pdf",
pages = "2690--2695",
abstract = "This paper presents a new active learning technique for machine translation based on quality estimation of automatically translated sentences. It uses an error-driven strategy, i.e., it assumes that the more errors an automatically translated sentence contains, the more informative it is for the translation system. Our approach is based on a quality estimation technique which involves a wider range of features of the source text, automatic translation, and machine translation system compared to previous work. In addition, we enhance the machine translation system training data with post-edited machine translations of the sentences selected, instead of simulating this using previously created reference translations. We found that re-training systems with additional post-edited data yields higher quality translations regardless of the selection strategy used. We relate this to the fact that post-editions tend to be closer to source sentences as compared to references, making the rule extraction process more reliable.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="logacheva-specia-2014-quality">
<titleInfo>
<title>A Quality-based Active Sample Selection Strategy for Statistical Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</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 paper presents a new active learning technique for machine translation based on quality estimation of automatically translated sentences. It uses an error-driven strategy, i.e., it assumes that the more errors an automatically translated sentence contains, the more informative it is for the translation system. Our approach is based on a quality estimation technique which involves a wider range of features of the source text, automatic translation, and machine translation system compared to previous work. In addition, we enhance the machine translation system training data with post-edited machine translations of the sentences selected, instead of simulating this using previously created reference translations. We found that re-training systems with additional post-edited data yields higher quality translations regardless of the selection strategy used. We relate this to the fact that post-editions tend to be closer to source sentences as compared to references, making the rule extraction process more reliable.</abstract>
<identifier type="citekey">logacheva-specia-2014-quality</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/658_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2690</start>
<end>2695</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Quality-based Active Sample Selection Strategy for Statistical Machine Translation
%A Logacheva, Varvara
%A Specia, Lucia
%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 logacheva-specia-2014-quality
%X This paper presents a new active learning technique for machine translation based on quality estimation of automatically translated sentences. It uses an error-driven strategy, i.e., it assumes that the more errors an automatically translated sentence contains, the more informative it is for the translation system. Our approach is based on a quality estimation technique which involves a wider range of features of the source text, automatic translation, and machine translation system compared to previous work. In addition, we enhance the machine translation system training data with post-edited machine translations of the sentences selected, instead of simulating this using previously created reference translations. We found that re-training systems with additional post-edited data yields higher quality translations regardless of the selection strategy used. We relate this to the fact that post-editions tend to be closer to source sentences as compared to references, making the rule extraction process more reliable.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/658_Paper.pdf
%P 2690-2695
Markdown (Informal)
[A Quality-based Active Sample Selection Strategy for Statistical Machine Translation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/658_Paper.pdf) (Logacheva & Specia, LREC 2014)
ACL