@inproceedings{cotterell-callison-burch-2014-multi,
title = "A Multi-Dialect, Multi-Genre Corpus of Informal Written {A}rabic",
author = "Cotterell, Ryan and
Callison-Burch, Chris",
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/641_Paper.pdf",
pages = "241--245",
abstract = "This paper presents a multi-dialect, multi-genre, human annotated corpus of dialectal Arabic. We collected utterances in five Arabic dialects: Levantine, Gulf, Egyptian, Iraqi and Maghrebi. We scraped newspaper websites for user commentary and Twitter for two distinct types of dialectal content. To the best of the authors knowledge, this work is the most diverse corpus of dialectal Arabic in both the source of the content and the number of dialects. Every utterance in the corpus was human annotated on Amazons Mechanical Turk; this stands in contrast to Al-Sabbagh and Girju (2012) where only a small subset was human annotated in order to train a classifier to automatically annotate the remainder of the corpus. We provide a discussion of the methodology used for the annotation in addition to the performance of the individual workers. We extend the Arabic dialect identification task to the Iraqi and Maghrebi dialects and improve the results of Zaidan and Callison-Burch (2011a) on Levantine, Gulf and Egyptian.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cotterell-callison-burch-2014-multi">
<titleInfo>
<title>A Multi-Dialect, Multi-Genre Corpus of Informal Written Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</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>This paper presents a multi-dialect, multi-genre, human annotated corpus of dialectal Arabic. We collected utterances in five Arabic dialects: Levantine, Gulf, Egyptian, Iraqi and Maghrebi. We scraped newspaper websites for user commentary and Twitter for two distinct types of dialectal content. To the best of the authors knowledge, this work is the most diverse corpus of dialectal Arabic in both the source of the content and the number of dialects. Every utterance in the corpus was human annotated on Amazons Mechanical Turk; this stands in contrast to Al-Sabbagh and Girju (2012) where only a small subset was human annotated in order to train a classifier to automatically annotate the remainder of the corpus. We provide a discussion of the methodology used for the annotation in addition to the performance of the individual workers. We extend the Arabic dialect identification task to the Iraqi and Maghrebi dialects and improve the results of Zaidan and Callison-Burch (2011a) on Levantine, Gulf and Egyptian.</abstract>
<identifier type="citekey">cotterell-callison-burch-2014-multi</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/641_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>241</start>
<end>245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-Dialect, Multi-Genre Corpus of Informal Written Arabic
%A Cotterell, Ryan
%A Callison-Burch, Chris
%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 cotterell-callison-burch-2014-multi
%X This paper presents a multi-dialect, multi-genre, human annotated corpus of dialectal Arabic. We collected utterances in five Arabic dialects: Levantine, Gulf, Egyptian, Iraqi and Maghrebi. We scraped newspaper websites for user commentary and Twitter for two distinct types of dialectal content. To the best of the authors knowledge, this work is the most diverse corpus of dialectal Arabic in both the source of the content and the number of dialects. Every utterance in the corpus was human annotated on Amazons Mechanical Turk; this stands in contrast to Al-Sabbagh and Girju (2012) where only a small subset was human annotated in order to train a classifier to automatically annotate the remainder of the corpus. We provide a discussion of the methodology used for the annotation in addition to the performance of the individual workers. We extend the Arabic dialect identification task to the Iraqi and Maghrebi dialects and improve the results of Zaidan and Callison-Burch (2011a) on Levantine, Gulf and Egyptian.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/641_Paper.pdf
%P 241-245
Markdown (Informal)
[A Multi-Dialect, Multi-Genre Corpus of Informal Written Arabic](http://www.lrec-conf.org/proceedings/lrec2014/pdf/641_Paper.pdf) (Cotterell & Callison-Burch, LREC 2014)
ACL