@inproceedings{eryani-etal-2020-spelling,
title = "A Spelling Correction Corpus for Multiple {A}rabic Dialects",
author = "Eryani, Fadhl and
Habash, Nizar and
Bouamor, Houda and
Khalifa, Salam",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.508",
pages = "4130--4138",
abstract = "Arabic dialects are the non-standard varieties of Arabic commonly spoken {--} and increasingly written on social media {--} across the Arab world. Arabic dialects do not have standard orthographies, a challenge for natural language processing applications. In this paper, we present the MADAR CODA Corpus, a collection of 10,000 sentences from five Arabic city dialects (Beirut, Cairo, Doha, Rabat, and Tunis) represented in the Conventional Orthography for Dialectal Arabic (CODA) in parallel with their raw original form. The sentences come from the Multi-Arabic Dialect Applications and Resources (MADAR) Project and are in parallel across the cities (2,000 sentences from each city). This publicly available resource is intended to support research on spelling correction and text normalization for Arabic dialects. We present results on a bootstrapping technique we use to speed up the CODA annotation, as well as on the degree of similarity across the dialects before and after CODA annotation.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eryani-etal-2020-spelling">
<titleInfo>
<title>A Spelling Correction Corpus for Multiple Arabic Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fadhl</namePart>
<namePart type="family">Eryani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Arabic dialects are the non-standard varieties of Arabic commonly spoken – and increasingly written on social media – across the Arab world. Arabic dialects do not have standard orthographies, a challenge for natural language processing applications. In this paper, we present the MADAR CODA Corpus, a collection of 10,000 sentences from five Arabic city dialects (Beirut, Cairo, Doha, Rabat, and Tunis) represented in the Conventional Orthography for Dialectal Arabic (CODA) in parallel with their raw original form. The sentences come from the Multi-Arabic Dialect Applications and Resources (MADAR) Project and are in parallel across the cities (2,000 sentences from each city). This publicly available resource is intended to support research on spelling correction and text normalization for Arabic dialects. We present results on a bootstrapping technique we use to speed up the CODA annotation, as well as on the degree of similarity across the dialects before and after CODA annotation.</abstract>
<identifier type="citekey">eryani-etal-2020-spelling</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.508</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4130</start>
<end>4138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Spelling Correction Corpus for Multiple Arabic Dialects
%A Eryani, Fadhl
%A Habash, Nizar
%A Bouamor, Houda
%A Khalifa, Salam
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F eryani-etal-2020-spelling
%X Arabic dialects are the non-standard varieties of Arabic commonly spoken – and increasingly written on social media – across the Arab world. Arabic dialects do not have standard orthographies, a challenge for natural language processing applications. In this paper, we present the MADAR CODA Corpus, a collection of 10,000 sentences from five Arabic city dialects (Beirut, Cairo, Doha, Rabat, and Tunis) represented in the Conventional Orthography for Dialectal Arabic (CODA) in parallel with their raw original form. The sentences come from the Multi-Arabic Dialect Applications and Resources (MADAR) Project and are in parallel across the cities (2,000 sentences from each city). This publicly available resource is intended to support research on spelling correction and text normalization for Arabic dialects. We present results on a bootstrapping technique we use to speed up the CODA annotation, as well as on the degree of similarity across the dialects before and after CODA annotation.
%U https://aclanthology.org/2020.lrec-1.508
%P 4130-4138
Markdown (Informal)
[A Spelling Correction Corpus for Multiple Arabic Dialects](https://aclanthology.org/2020.lrec-1.508) (Eryani et al., LREC 2020)
ACL