@inproceedings{baimukan-etal-2022-hierarchical,
title = "Hierarchical Aggregation of Dialectal Data for {A}rabic Dialect Identification",
author = "Baimukan, Nurpeiis and
Bouamor, Houda and
Habash, Nizar",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.489",
pages = "4586--4596",
abstract = "Arabic is a collection of dialectal variants that are historically related but significantly different. These differences can be seen across regions, countries, and even cities in the same countries. Previous work on Arabic Dialect identification has focused mainly on specific dialect levels (region, country, province, or city) using level-specific resources; and different efforts used different schemas and labels. In this paper, we present the first effort aiming at defining a standard unified three-level hierarchical schema (region-country-city) for dialectal Arabic classification. We map 29 different data sets to this unified schema, and use the common mapping to facilitate aggregating these data sets. We test the value of such aggregation by building language models and using them in dialect identification. We make our label mapping code and aggregated language models publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baimukan-etal-2022-hierarchical">
<titleInfo>
<title>Hierarchical Aggregation of Dialectal Data for Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nurpeiis</namePart>
<namePart type="family">Baimukan</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">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>Arabic is a collection of dialectal variants that are historically related but significantly different. These differences can be seen across regions, countries, and even cities in the same countries. Previous work on Arabic Dialect identification has focused mainly on specific dialect levels (region, country, province, or city) using level-specific resources; and different efforts used different schemas and labels. In this paper, we present the first effort aiming at defining a standard unified three-level hierarchical schema (region-country-city) for dialectal Arabic classification. We map 29 different data sets to this unified schema, and use the common mapping to facilitate aggregating these data sets. We test the value of such aggregation by building language models and using them in dialect identification. We make our label mapping code and aggregated language models publicly available.</abstract>
<identifier type="citekey">baimukan-etal-2022-hierarchical</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.489</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4586</start>
<end>4596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Aggregation of Dialectal Data for Arabic Dialect Identification
%A Baimukan, Nurpeiis
%A Bouamor, Houda
%A Habash, Nizar
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F baimukan-etal-2022-hierarchical
%X Arabic is a collection of dialectal variants that are historically related but significantly different. These differences can be seen across regions, countries, and even cities in the same countries. Previous work on Arabic Dialect identification has focused mainly on specific dialect levels (region, country, province, or city) using level-specific resources; and different efforts used different schemas and labels. In this paper, we present the first effort aiming at defining a standard unified three-level hierarchical schema (region-country-city) for dialectal Arabic classification. We map 29 different data sets to this unified schema, and use the common mapping to facilitate aggregating these data sets. We test the value of such aggregation by building language models and using them in dialect identification. We make our label mapping code and aggregated language models publicly available.
%U https://aclanthology.org/2022.lrec-1.489
%P 4586-4596
Markdown (Informal)
[Hierarchical Aggregation of Dialectal Data for Arabic Dialect Identification](https://aclanthology.org/2022.lrec-1.489) (Baimukan et al., LREC 2022)
ACL