@inproceedings{fairon-paumier-2006-translated,
title = "A translated corpus of 30,000 {F}rench {SMS}",
author = "Fairon, C{\'e}drick and
Paumier, S{\'e}bastien",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/270_pdf.pdf",
abstract = "The development of communication technologies has contributed to the appearance of new forms in the written language that scientists have to study according to their peculiarities (typing or viewing constraints, synchronicity, etc). In the particular case of SMS (Short Message Service), studies are complicated by a lack of data, mainly due to technical constraints and privacy considerations. In this paper, we present a corpus of 30,000 French SMS collected through a project in Belgium named Faites don de vos SMS {\`a} la science (Give your SMS to Science). This corpus is unique in its quality, its size and the fact that the SMS have been manually translated into standard French. We will first describe the collection process and discuss the writers' profiles. Then we will explain in detail how the translation was carried out.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fairon-paumier-2006-translated">
<titleInfo>
<title>A translated corpus of 30,000 French SMS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cédrick</namePart>
<namePart type="family">Fairon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sébastien</namePart>
<namePart type="family">Paumier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of communication technologies has contributed to the appearance of new forms in the written language that scientists have to study according to their peculiarities (typing or viewing constraints, synchronicity, etc). In the particular case of SMS (Short Message Service), studies are complicated by a lack of data, mainly due to technical constraints and privacy considerations. In this paper, we present a corpus of 30,000 French SMS collected through a project in Belgium named Faites don de vos SMS à la science (Give your SMS to Science). This corpus is unique in its quality, its size and the fact that the SMS have been manually translated into standard French. We will first describe the collection process and discuss the writers’ profiles. Then we will explain in detail how the translation was carried out.</abstract>
<identifier type="citekey">fairon-paumier-2006-translated</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/270_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A translated corpus of 30,000 French SMS
%A Fairon, Cédrick
%A Paumier, Sébastien
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F fairon-paumier-2006-translated
%X The development of communication technologies has contributed to the appearance of new forms in the written language that scientists have to study according to their peculiarities (typing or viewing constraints, synchronicity, etc). In the particular case of SMS (Short Message Service), studies are complicated by a lack of data, mainly due to technical constraints and privacy considerations. In this paper, we present a corpus of 30,000 French SMS collected through a project in Belgium named Faites don de vos SMS à la science (Give your SMS to Science). This corpus is unique in its quality, its size and the fact that the SMS have been manually translated into standard French. We will first describe the collection process and discuss the writers’ profiles. Then we will explain in detail how the translation was carried out.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/270_pdf.pdf
Markdown (Informal)
[A translated corpus of 30,000 French SMS](http://www.lrec-conf.org/proceedings/lrec2006/pdf/270_pdf.pdf) (Fairon & Paumier, LREC 2006)
ACL
- Cédrick Fairon and Sébastien Paumier. 2006. A translated corpus of 30,000 French SMS. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).