@inproceedings{jamal-etal-2022-arabic,
title = "On The {A}rabic Dialects' Identification: Overcoming Challenges of Geographical Similarities Between {A}rabic dialects and Imbalanced Datasets",
author = "Jamal, Salma and
.Kassem, Aly M and
Mohamed, Omar and
Ashraf, Ali",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.49/",
doi = "10.18653/v1/2022.wanlp-1.49",
pages = "458--463",
abstract = "Arabic is one of the world`s richest languages, with a diverse range of dialects based on geographical origin. In this paper, we present a solution to tackle subtask 1 (Country-level dialect identification) of the Nuanced Arabic Dialect Identification (NADI) shared task 2022 achieving third place with an average macro F1 score between the two test sets of 26.44{\%}. In the preprocessing stage, we removed the most common frequent terms from all sentences across all dialects, and in the modeling step, we employed a hybrid loss function approach that includes Weighted cross entropy loss and Vector Scaling(VS) Loss. On test sets A and B, our model achieved 35.68{\%} and 17.192{\%} Macro F1 scores, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jamal-etal-2022-arabic">
<titleInfo>
<title>On The Arabic Dialects’ Identification: Overcoming Challenges of Geographical Similarities Between Arabic dialects and Imbalanced Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salma</namePart>
<namePart type="family">Jamal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aly</namePart>
<namePart type="given">M</namePart>
<namePart type="family">.Kassem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<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">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</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">Ahmed</namePart>
<namePart type="family">Abdelali</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">Salam</namePart>
<namePart type="family">Khalifa</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">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Arabic is one of the world‘s richest languages, with a diverse range of dialects based on geographical origin. In this paper, we present a solution to tackle subtask 1 (Country-level dialect identification) of the Nuanced Arabic Dialect Identification (NADI) shared task 2022 achieving third place with an average macro F1 score between the two test sets of 26.44%. In the preprocessing stage, we removed the most common frequent terms from all sentences across all dialects, and in the modeling step, we employed a hybrid loss function approach that includes Weighted cross entropy loss and Vector Scaling(VS) Loss. On test sets A and B, our model achieved 35.68% and 17.192% Macro F1 scores, respectively.</abstract>
<identifier type="citekey">jamal-etal-2022-arabic</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.49</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.49/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>458</start>
<end>463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On The Arabic Dialects’ Identification: Overcoming Challenges of Geographical Similarities Between Arabic dialects and Imbalanced Datasets
%A Jamal, Salma
%A .Kassem, Aly M.
%A Mohamed, Omar
%A Ashraf, Ali
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F jamal-etal-2022-arabic
%X Arabic is one of the world‘s richest languages, with a diverse range of dialects based on geographical origin. In this paper, we present a solution to tackle subtask 1 (Country-level dialect identification) of the Nuanced Arabic Dialect Identification (NADI) shared task 2022 achieving third place with an average macro F1 score between the two test sets of 26.44%. In the preprocessing stage, we removed the most common frequent terms from all sentences across all dialects, and in the modeling step, we employed a hybrid loss function approach that includes Weighted cross entropy loss and Vector Scaling(VS) Loss. On test sets A and B, our model achieved 35.68% and 17.192% Macro F1 scores, respectively.
%R 10.18653/v1/2022.wanlp-1.49
%U https://aclanthology.org/2022.wanlp-1.49/
%U https://doi.org/10.18653/v1/2022.wanlp-1.49
%P 458-463
Markdown (Informal)
[On The Arabic Dialects’ Identification: Overcoming Challenges of Geographical Similarities Between Arabic dialects and Imbalanced Datasets](https://aclanthology.org/2022.wanlp-1.49/) (Jamal et al., WANLP 2022)
ACL