@inproceedings{stepanov-etal-2014-development,
title = "The Development of the Multilingual {LUNA} Corpus for Spoken Language System Porting",
author = "Stepanov, Evgeny and
Riccardi, Giuseppe and
Bayer, Ali Orkan",
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/789_Paper.pdf",
pages = "2675--2678",
abstract = "The development of annotated corpora is a critical process in the development of speech applications for multiple target languages. While the technology to develop a monolingual speech application has reached satisfactory results (in terms of performance and effort), porting an existing application from a source language to a target language is still a very expensive task. In this paper we address the problem of creating multilingual aligned corpora and its evaluation in the context of a spoken language understanding (SLU) porting task. We discuss the challenges of the manual creation of multilingual corpora, as well as present the algorithms for the creation of multilingual SLU via Statistical Machine Translation (SMT).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stepanov-etal-2014-development">
<titleInfo>
<title>The Development of the Multilingual LUNA Corpus for Spoken Language System Porting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Evgeny</namePart>
<namePart type="family">Stepanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Riccardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="given">Orkan</namePart>
<namePart type="family">Bayer</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 development of annotated corpora is a critical process in the development of speech applications for multiple target languages. While the technology to develop a monolingual speech application has reached satisfactory results (in terms of performance and effort), porting an existing application from a source language to a target language is still a very expensive task. In this paper we address the problem of creating multilingual aligned corpora and its evaluation in the context of a spoken language understanding (SLU) porting task. We discuss the challenges of the manual creation of multilingual corpora, as well as present the algorithms for the creation of multilingual SLU via Statistical Machine Translation (SMT).</abstract>
<identifier type="citekey">stepanov-etal-2014-development</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/789_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2675</start>
<end>2678</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Development of the Multilingual LUNA Corpus for Spoken Language System Porting
%A Stepanov, Evgeny
%A Riccardi, Giuseppe
%A Bayer, Ali Orkan
%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 stepanov-etal-2014-development
%X The development of annotated corpora is a critical process in the development of speech applications for multiple target languages. While the technology to develop a monolingual speech application has reached satisfactory results (in terms of performance and effort), porting an existing application from a source language to a target language is still a very expensive task. In this paper we address the problem of creating multilingual aligned corpora and its evaluation in the context of a spoken language understanding (SLU) porting task. We discuss the challenges of the manual creation of multilingual corpora, as well as present the algorithms for the creation of multilingual SLU via Statistical Machine Translation (SMT).
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/789_Paper.pdf
%P 2675-2678
Markdown (Informal)
[The Development of the Multilingual LUNA Corpus for Spoken Language System Porting](http://www.lrec-conf.org/proceedings/lrec2014/pdf/789_Paper.pdf) (Stepanov et al., LREC 2014)
ACL