@inproceedings{voss-etal-2014-finding,
title = "Finding {R}omanized {A}rabic Dialect in Code-Mixed Tweets",
author = "Voss, Clare and
Tratz, Stephen and
Laoudi, Jamal and
Briesch, Douglas",
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/1116_Paper.pdf",
pages = "2249--2253",
abstract = "Recent computational work on Arabic dialect identification has focused primarily on building and annotating corpora written in Arabic script. Arabic dialects however also appear written in Roman script, especially in social media. This paper describes our recent work developing tweet corpora and a token-level classifier that identifies a Romanized Arabic dialect and distinguishes it from French and English in tweets. We focus on Moroccan Darija, one of several spoken vernaculars in the family of Maghrebi Arabic dialects. Even given noisy, code-mixed tweets,the classifier achieved token-level recall of 93.2{\%} on Romanized Arabic dialect, 83.2{\%} on English, and 90.1{\%} on French. The classifier, now integrated into our tweet conversation annotation tool (Tratz et al. 2013), has semi-automated the construction of a Romanized Arabic-dialect lexicon. Two datasets, a full list of Moroccan Darija surface token forms and a table of lexical entries derived from this list with spelling variants, as extracted from our tweet corpus collection, will be made available in the LRE MAP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="voss-etal-2014-finding">
<titleInfo>
<title>Finding Romanized Arabic Dialect in Code-Mixed Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Clare</namePart>
<namePart type="family">Voss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Tratz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamal</namePart>
<namePart type="family">Laoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Briesch</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>Recent computational work on Arabic dialect identification has focused primarily on building and annotating corpora written in Arabic script. Arabic dialects however also appear written in Roman script, especially in social media. This paper describes our recent work developing tweet corpora and a token-level classifier that identifies a Romanized Arabic dialect and distinguishes it from French and English in tweets. We focus on Moroccan Darija, one of several spoken vernaculars in the family of Maghrebi Arabic dialects. Even given noisy, code-mixed tweets,the classifier achieved token-level recall of 93.2% on Romanized Arabic dialect, 83.2% on English, and 90.1% on French. The classifier, now integrated into our tweet conversation annotation tool (Tratz et al. 2013), has semi-automated the construction of a Romanized Arabic-dialect lexicon. Two datasets, a full list of Moroccan Darija surface token forms and a table of lexical entries derived from this list with spelling variants, as extracted from our tweet corpus collection, will be made available in the LRE MAP.</abstract>
<identifier type="citekey">voss-etal-2014-finding</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1116_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2249</start>
<end>2253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finding Romanized Arabic Dialect in Code-Mixed Tweets
%A Voss, Clare
%A Tratz, Stephen
%A Laoudi, Jamal
%A Briesch, Douglas
%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 voss-etal-2014-finding
%X Recent computational work on Arabic dialect identification has focused primarily on building and annotating corpora written in Arabic script. Arabic dialects however also appear written in Roman script, especially in social media. This paper describes our recent work developing tweet corpora and a token-level classifier that identifies a Romanized Arabic dialect and distinguishes it from French and English in tweets. We focus on Moroccan Darija, one of several spoken vernaculars in the family of Maghrebi Arabic dialects. Even given noisy, code-mixed tweets,the classifier achieved token-level recall of 93.2% on Romanized Arabic dialect, 83.2% on English, and 90.1% on French. The classifier, now integrated into our tweet conversation annotation tool (Tratz et al. 2013), has semi-automated the construction of a Romanized Arabic-dialect lexicon. Two datasets, a full list of Moroccan Darija surface token forms and a table of lexical entries derived from this list with spelling variants, as extracted from our tweet corpus collection, will be made available in the LRE MAP.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1116_Paper.pdf
%P 2249-2253
Markdown (Informal)
[Finding Romanized Arabic Dialect in Code-Mixed Tweets](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1116_Paper.pdf) (Voss et al., LREC 2014)
ACL
- Clare Voss, Stephen Tratz, Jamal Laoudi, and Douglas Briesch. 2014. Finding Romanized Arabic Dialect in Code-Mixed Tweets. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2249–2253, Reykjavik, Iceland. European Language Resources Association (ELRA).