@inproceedings{elkaref-etal-2023-nlpeople-nadi,
title = "{NLP}eople at {NADI} 2023 Shared Task: {A}rabic Dialect Identification with Augmented Context and Multi-Stage Tuning",
author = "Elkaref, Mohab and
Moses, Movina and
Tanaka, Shinnosuke and
Barry, James and
Mel, Geeth",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.68",
doi = "10.18653/v1/2023.arabicnlp-1.68",
pages = "642--646",
abstract = "This paper presents the approach of the NLPeople team to the Nuanced Arabic Dialect Identification (NADI) 2023 shared task. Subtask 1 involves identifying the dialect of a source text at the country level. Our approach to Subtask 1 makes use of language-specific language models, a clustering and retrieval method to provide additional context to a target sentence, a fine-tuning strategy which makes use of the provided data from the 2020 and 2021 shared tasks, and finally, ensembling over the predictions of multiple models. Our submission achieves a macro-averaged F1 score of 87.27, ranking 1st among the other participants in the task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elkaref-etal-2023-nlpeople-nadi">
<titleInfo>
<title>NLPeople at NADI 2023 Shared Task: Arabic Dialect Identification with Augmented Context and Multi-Stage Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohab</namePart>
<namePart type="family">Elkaref</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Movina</namePart>
<namePart type="family">Moses</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinnosuke</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Barry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeth</namePart>
<namePart type="family">Mel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</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">Walid</namePart>
<namePart type="family">Magdy</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">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the approach of the NLPeople team to the Nuanced Arabic Dialect Identification (NADI) 2023 shared task. Subtask 1 involves identifying the dialect of a source text at the country level. Our approach to Subtask 1 makes use of language-specific language models, a clustering and retrieval method to provide additional context to a target sentence, a fine-tuning strategy which makes use of the provided data from the 2020 and 2021 shared tasks, and finally, ensembling over the predictions of multiple models. Our submission achieves a macro-averaged F1 score of 87.27, ranking 1st among the other participants in the task.</abstract>
<identifier type="citekey">elkaref-etal-2023-nlpeople-nadi</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.68</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.68</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>642</start>
<end>646</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLPeople at NADI 2023 Shared Task: Arabic Dialect Identification with Augmented Context and Multi-Stage Tuning
%A Elkaref, Mohab
%A Moses, Movina
%A Tanaka, Shinnosuke
%A Barry, James
%A Mel, Geeth
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F elkaref-etal-2023-nlpeople-nadi
%X This paper presents the approach of the NLPeople team to the Nuanced Arabic Dialect Identification (NADI) 2023 shared task. Subtask 1 involves identifying the dialect of a source text at the country level. Our approach to Subtask 1 makes use of language-specific language models, a clustering and retrieval method to provide additional context to a target sentence, a fine-tuning strategy which makes use of the provided data from the 2020 and 2021 shared tasks, and finally, ensembling over the predictions of multiple models. Our submission achieves a macro-averaged F1 score of 87.27, ranking 1st among the other participants in the task.
%R 10.18653/v1/2023.arabicnlp-1.68
%U https://aclanthology.org/2023.arabicnlp-1.68
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.68
%P 642-646
Markdown (Informal)
[NLPeople at NADI 2023 Shared Task: Arabic Dialect Identification with Augmented Context and Multi-Stage Tuning](https://aclanthology.org/2023.arabicnlp-1.68) (Elkaref et al., ArabicNLP-WS 2023)
ACL