@inproceedings{veeramani-etal-2023-dialectnlu,
title = "{D}ialect{NLU} at {NADI} 2023 Shared Task: Transformer Based Multitask Approach Jointly Integrating Dialect and Machine Translation Tasks in {A}rabic",
author = "Veeramani, Hariram and
Thapa, Surendrabikram and
Naseem, Usman",
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-1.63",
doi = "10.18653/v1/2023.arabicnlp-1.63",
pages = "614--619",
abstract = "With approximately 400 million speakers worldwide, Arabic ranks as the fifth most-spoken language globally, necessitating advancements in natural language processing. This paper addresses this need by presenting a system description of the approaches employed for the subtasks outlined in the Nuanced Arabic Dialect Identification (NADI) task at EMNLP 2023. For the first subtask, involving closed country-level dialect identification classification, we employ an ensemble of two Arabic language models. Similarly, for the second subtask, focused on closed dialect to Modern Standard Arabic (MSA) machine translation, our approach combines sequence-to-sequence models, all trained on an Arabic-specific dataset. Our team ranks 10th and 3rd on subtask 1 and subtask 2 respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="veeramani-etal-2023-dialectnlu">
<titleInfo>
<title>DialectNLU at NADI 2023 Shared Task: Transformer Based Multitask Approach Jointly Integrating Dialect and Machine Translation Tasks in Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hariram</namePart>
<namePart type="family">Veeramani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Naseem</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>With approximately 400 million speakers worldwide, Arabic ranks as the fifth most-spoken language globally, necessitating advancements in natural language processing. This paper addresses this need by presenting a system description of the approaches employed for the subtasks outlined in the Nuanced Arabic Dialect Identification (NADI) task at EMNLP 2023. For the first subtask, involving closed country-level dialect identification classification, we employ an ensemble of two Arabic language models. Similarly, for the second subtask, focused on closed dialect to Modern Standard Arabic (MSA) machine translation, our approach combines sequence-to-sequence models, all trained on an Arabic-specific dataset. Our team ranks 10th and 3rd on subtask 1 and subtask 2 respectively.</abstract>
<identifier type="citekey">veeramani-etal-2023-dialectnlu</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.63</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.63</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>614</start>
<end>619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DialectNLU at NADI 2023 Shared Task: Transformer Based Multitask Approach Jointly Integrating Dialect and Machine Translation Tasks in Arabic
%A Veeramani, Hariram
%A Thapa, Surendrabikram
%A Naseem, Usman
%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 veeramani-etal-2023-dialectnlu
%X With approximately 400 million speakers worldwide, Arabic ranks as the fifth most-spoken language globally, necessitating advancements in natural language processing. This paper addresses this need by presenting a system description of the approaches employed for the subtasks outlined in the Nuanced Arabic Dialect Identification (NADI) task at EMNLP 2023. For the first subtask, involving closed country-level dialect identification classification, we employ an ensemble of two Arabic language models. Similarly, for the second subtask, focused on closed dialect to Modern Standard Arabic (MSA) machine translation, our approach combines sequence-to-sequence models, all trained on an Arabic-specific dataset. Our team ranks 10th and 3rd on subtask 1 and subtask 2 respectively.
%R 10.18653/v1/2023.arabicnlp-1.63
%U https://aclanthology.org/2023.arabicnlp-1.63
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.63
%P 614-619
Markdown (Informal)
[DialectNLU at NADI 2023 Shared Task: Transformer Based Multitask Approach Jointly Integrating Dialect and Machine Translation Tasks in Arabic](https://aclanthology.org/2023.arabicnlp-1.63) (Veeramani et al., ArabicNLP-WS 2023)
ACL