@inproceedings{wadhawan-2021-dialect,
title = "Dialect Identification in Nuanced {A}rabic Tweets Using Farasa Segmentation and {A}ra{BERT}",
author = "Wadhawan, Anshul",
editor = "Habash, Nizar and
Bouamor, Houda and
Hajj, Hazem and
Magdy, Walid and
Zaghouani, Wajdi and
Bougares, Fethi and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Touileb, Samia",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wanlp-1.35",
pages = "291--295",
abstract = "This paper presents our approach to address the EACL WANLP-2021 Shared Task 1: Nuanced Arabic Dialect Identification (NADI). The task is aimed at developing a system that identifies the geographical location(country/province) from where an Arabic tweet in the form of modern standard Arabic or dialect comes from. We solve the task in two parts. The first part involves pre-processing the provided dataset by cleaning, adding and segmenting various parts of the text. This is followed by carrying out experiments with different versions of two Transformer based models, AraBERT and AraELECTRA. Our final approach achieved macro F1-scores of 0.216, 0.235, 0.054, and 0.043 in the four subtasks, and we were ranked second in MSA identification subtasks and fourth in DA identification subtasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wadhawan-2021-dialect">
<titleInfo>
<title>Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anshul</namePart>
<namePart type="family">Wadhawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</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">Hazem</namePart>
<namePart type="family">Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</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>
<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">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our approach to address the EACL WANLP-2021 Shared Task 1: Nuanced Arabic Dialect Identification (NADI). The task is aimed at developing a system that identifies the geographical location(country/province) from where an Arabic tweet in the form of modern standard Arabic or dialect comes from. We solve the task in two parts. The first part involves pre-processing the provided dataset by cleaning, adding and segmenting various parts of the text. This is followed by carrying out experiments with different versions of two Transformer based models, AraBERT and AraELECTRA. Our final approach achieved macro F1-scores of 0.216, 0.235, 0.054, and 0.043 in the four subtasks, and we were ranked second in MSA identification subtasks and fourth in DA identification subtasks.</abstract>
<identifier type="citekey">wadhawan-2021-dialect</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.35</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>291</start>
<end>295</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT
%A Wadhawan, Anshul
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Hajj, Hazem
%Y Magdy, Walid
%Y Zaghouani, Wajdi
%Y Bougares, Fethi
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Touileb, Samia
%S Proceedings of the Sixth Arabic Natural Language Processing Workshop
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine (Virtual)
%F wadhawan-2021-dialect
%X This paper presents our approach to address the EACL WANLP-2021 Shared Task 1: Nuanced Arabic Dialect Identification (NADI). The task is aimed at developing a system that identifies the geographical location(country/province) from where an Arabic tweet in the form of modern standard Arabic or dialect comes from. We solve the task in two parts. The first part involves pre-processing the provided dataset by cleaning, adding and segmenting various parts of the text. This is followed by carrying out experiments with different versions of two Transformer based models, AraBERT and AraELECTRA. Our final approach achieved macro F1-scores of 0.216, 0.235, 0.054, and 0.043 in the four subtasks, and we were ranked second in MSA identification subtasks and fourth in DA identification subtasks.
%U https://aclanthology.org/2021.wanlp-1.35
%P 291-295
Markdown (Informal)
[Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT](https://aclanthology.org/2021.wanlp-1.35) (Wadhawan, WANLP 2021)
ACL