@inproceedings{el-mekki-etal-2020-weighted,
title = "Weighted combination of {BERT} and N-{GRAM} features for Nuanced {A}rabic Dialect Identification",
author = "El Mekki, Abdellah and
Alami, Ahmed and
Alami, Hamza and
Khoumsi, Ahmed and
Berrada, Ismail",
editor = "Zitouni, Imed and
Abdul-Mageed, Muhammad and
Bouamor, Houda and
Bougares, Fethi and
El-Haj, Mahmoud and
Tomeh, Nadi and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wanlp-1.27",
pages = "268--274",
abstract = "Around the Arab world, different Arabic dialects are spoken by more than 300M persons, and are increasingly popular in social media texts. However, Arabic dialects are considered to be low-resource languages, limiting the development of machine-learning based systems for these dialects. In this paper, we investigate the Arabic dialect identification task, from two perspectives: country-level dialect identification from 21 Arab countries, and province-level dialect identification from 100 provinces. We introduce an unified pipeline of state-of-the-art models, that can handle the two subtasks. Our experimental studies applied to the NADI shared task, show promising results both at the country-level (F1-score of 25.99{\%}) and the province-level (F1-score of 6.39{\%}), and thus allow us to be ranked 2nd for the country-level subtask, and 1st in the province-level subtask.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-mekki-etal-2020-weighted">
<titleInfo>
<title>Weighted combination of BERT and N-GRAM features for Nuanced Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Alami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamza</namePart>
<namePart type="family">Alami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Khoumsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismail</namePart>
<namePart type="family">Berrada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Around the Arab world, different Arabic dialects are spoken by more than 300M persons, and are increasingly popular in social media texts. However, Arabic dialects are considered to be low-resource languages, limiting the development of machine-learning based systems for these dialects. In this paper, we investigate the Arabic dialect identification task, from two perspectives: country-level dialect identification from 21 Arab countries, and province-level dialect identification from 100 provinces. We introduce an unified pipeline of state-of-the-art models, that can handle the two subtasks. Our experimental studies applied to the NADI shared task, show promising results both at the country-level (F1-score of 25.99%) and the province-level (F1-score of 6.39%), and thus allow us to be ranked 2nd for the country-level subtask, and 1st in the province-level subtask.</abstract>
<identifier type="citekey">el-mekki-etal-2020-weighted</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.27</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>268</start>
<end>274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weighted combination of BERT and N-GRAM features for Nuanced Arabic Dialect Identification
%A El Mekki, Abdellah
%A Alami, Ahmed
%A Alami, Hamza
%A Khoumsi, Ahmed
%A Berrada, Ismail
%Y Zitouni, Imed
%Y Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Bougares, Fethi
%Y El-Haj, Mahmoud
%Y Tomeh, Nadi
%Y Zaghouani, Wajdi
%S Proceedings of the Fifth Arabic Natural Language Processing Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F el-mekki-etal-2020-weighted
%X Around the Arab world, different Arabic dialects are spoken by more than 300M persons, and are increasingly popular in social media texts. However, Arabic dialects are considered to be low-resource languages, limiting the development of machine-learning based systems for these dialects. In this paper, we investigate the Arabic dialect identification task, from two perspectives: country-level dialect identification from 21 Arab countries, and province-level dialect identification from 100 provinces. We introduce an unified pipeline of state-of-the-art models, that can handle the two subtasks. Our experimental studies applied to the NADI shared task, show promising results both at the country-level (F1-score of 25.99%) and the province-level (F1-score of 6.39%), and thus allow us to be ranked 2nd for the country-level subtask, and 1st in the province-level subtask.
%U https://aclanthology.org/2020.wanlp-1.27
%P 268-274
Markdown (Informal)
[Weighted combination of BERT and N-GRAM features for Nuanced Arabic Dialect Identification](https://aclanthology.org/2020.wanlp-1.27) (El Mekki et al., WANLP 2020)
ACL