@inproceedings{gavrila-etal-2012-domain,
title = "Same domain different discourse style - A case study on Language Resources for data-driven Machine Translation",
author = "Gavrila, Monica and
v. Hahn, Walther and
Vertan, Cristina",
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/1003_Paper.pdf",
pages = "3441--3446",
abstract = "Data-driven machine translation (MT) approaches became very popular during last years, especially for language pairs for which it is difficult to find specialists to develop transfer rules. Statistical (SMT) or example-based (EBMT) systems can provide reasonable translation quality for assimilation purposes, as long as a large amount of training data is available. Especially SMT systems rely on parallel aligned corpora which have to be statistical relevant for the given language pair. The construction of large domain specific parallel corpora is time- and cost-consuming; the current practice relies on one or two big such corpora per language pair. Recent developed strategies ensure certain portability to other domains through specialized lexicons or small domain specific corpora. In this paper we discuss the influence of different discourse styles on statistical machine translation systems. We investigate how a pure SMT performs when training and test data belong to same domain but the discourse style varies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gavrila-etal-2012-domain">
<titleInfo>
<title>Same domain different discourse style - A case study on Language Resources for data-driven Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Gavrila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walther</namePart>
<namePart type="family">v. Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Vertan</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>Data-driven machine translation (MT) approaches became very popular during last years, especially for language pairs for which it is difficult to find specialists to develop transfer rules. Statistical (SMT) or example-based (EBMT) systems can provide reasonable translation quality for assimilation purposes, as long as a large amount of training data is available. Especially SMT systems rely on parallel aligned corpora which have to be statistical relevant for the given language pair. The construction of large domain specific parallel corpora is time- and cost-consuming; the current practice relies on one or two big such corpora per language pair. Recent developed strategies ensure certain portability to other domains through specialized lexicons or small domain specific corpora. In this paper we discuss the influence of different discourse styles on statistical machine translation systems. We investigate how a pure SMT performs when training and test data belong to same domain but the discourse style varies.</abstract>
<identifier type="citekey">gavrila-etal-2012-domain</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1003_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3441</start>
<end>3446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Same domain different discourse style - A case study on Language Resources for data-driven Machine Translation
%A Gavrila, Monica
%A v. Hahn, Walther
%A Vertan, Cristina
%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 gavrila-etal-2012-domain
%X Data-driven machine translation (MT) approaches became very popular during last years, especially for language pairs for which it is difficult to find specialists to develop transfer rules. Statistical (SMT) or example-based (EBMT) systems can provide reasonable translation quality for assimilation purposes, as long as a large amount of training data is available. Especially SMT systems rely on parallel aligned corpora which have to be statistical relevant for the given language pair. The construction of large domain specific parallel corpora is time- and cost-consuming; the current practice relies on one or two big such corpora per language pair. Recent developed strategies ensure certain portability to other domains through specialized lexicons or small domain specific corpora. In this paper we discuss the influence of different discourse styles on statistical machine translation systems. We investigate how a pure SMT performs when training and test data belong to same domain but the discourse style varies.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1003_Paper.pdf
%P 3441-3446
Markdown (Informal)
[Same domain different discourse style - A case study on Language Resources for data-driven Machine Translation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1003_Paper.pdf) (Gavrila et al., LREC 2012)
ACL