@inproceedings{lavergne-etal-2014-automatic,
title = "Automatic language identity tagging on word and sentence-level in multilingual text sources: a case-study on {L}uxembourgish",
author = "Lavergne, Thomas and
Adda, Gilles and
Adda-Decker, Martine and
Lamel, Lori",
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/732_Paper.pdf",
pages = "3300--3304",
abstract = "Luxembourgish, embedded in a multilingual context on the divide between Romance and Germanic cultures, remains one of Europe{'}s under-described languages. This is due to the fact that the written production remains relatively low, and linguistic knowledge and resources, such as lexica and pronunciation dictionaries, are sparse. The speakers or writers will frequently switch between Luxembourgish, German, and French, on a per-sentence basis, as well as on a sub-sentence level. In order to build resources like lexicons, and especially pronunciation lexicons, or language models needed for natural language processing tasks such as automatic speech recognition, language used in text corpora should be identified. In this paper, we present the design of a manually annotated corpus of mixed language sentences as well as the tools used to select these sentences. This corpus of difficult sentences was used to test a word-based language identification system. This language identification system was used to select textual data extracted from the web, in order to build a lexicon and language models. This lexicon and language model were used in an Automatic Speech Recognition system for the Luxembourgish language which obtain a 25{\%} WER on the Quaero development data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lavergne-etal-2014-automatic">
<titleInfo>
<title>Automatic language identity tagging on word and sentence-level in multilingual text sources: a case-study on Luxembourgish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Lavergne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Adda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martine</namePart>
<namePart type="family">Adda-Decker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lori</namePart>
<namePart type="family">Lamel</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>Luxembourgish, embedded in a multilingual context on the divide between Romance and Germanic cultures, remains one of Europe’s under-described languages. This is due to the fact that the written production remains relatively low, and linguistic knowledge and resources, such as lexica and pronunciation dictionaries, are sparse. The speakers or writers will frequently switch between Luxembourgish, German, and French, on a per-sentence basis, as well as on a sub-sentence level. In order to build resources like lexicons, and especially pronunciation lexicons, or language models needed for natural language processing tasks such as automatic speech recognition, language used in text corpora should be identified. In this paper, we present the design of a manually annotated corpus of mixed language sentences as well as the tools used to select these sentences. This corpus of difficult sentences was used to test a word-based language identification system. This language identification system was used to select textual data extracted from the web, in order to build a lexicon and language models. This lexicon and language model were used in an Automatic Speech Recognition system for the Luxembourgish language which obtain a 25% WER on the Quaero development data.</abstract>
<identifier type="citekey">lavergne-etal-2014-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/732_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3300</start>
<end>3304</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic language identity tagging on word and sentence-level in multilingual text sources: a case-study on Luxembourgish
%A Lavergne, Thomas
%A Adda, Gilles
%A Adda-Decker, Martine
%A Lamel, Lori
%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 lavergne-etal-2014-automatic
%X Luxembourgish, embedded in a multilingual context on the divide between Romance and Germanic cultures, remains one of Europe’s under-described languages. This is due to the fact that the written production remains relatively low, and linguistic knowledge and resources, such as lexica and pronunciation dictionaries, are sparse. The speakers or writers will frequently switch between Luxembourgish, German, and French, on a per-sentence basis, as well as on a sub-sentence level. In order to build resources like lexicons, and especially pronunciation lexicons, or language models needed for natural language processing tasks such as automatic speech recognition, language used in text corpora should be identified. In this paper, we present the design of a manually annotated corpus of mixed language sentences as well as the tools used to select these sentences. This corpus of difficult sentences was used to test a word-based language identification system. This language identification system was used to select textual data extracted from the web, in order to build a lexicon and language models. This lexicon and language model were used in an Automatic Speech Recognition system for the Luxembourgish language which obtain a 25% WER on the Quaero development data.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/732_Paper.pdf
%P 3300-3304
Markdown (Informal)
[Automatic language identity tagging on word and sentence-level in multilingual text sources: a case-study on Luxembourgish](http://www.lrec-conf.org/proceedings/lrec2014/pdf/732_Paper.pdf) (Lavergne et al., LREC 2014)
ACL