@inproceedings{shammary-etal-2022-tf,
title = "{TF}-{IDF} or Transformers for {A}rabic Dialect Identification? {ITFLOWS} participation in the {NADI} 2022 Shared Task",
author = "Shammary, Fouad and
Chen, Yiyi and
Kardkovacs, Zsolt T and
Alam, Mehwish and
Afli, Haithem",
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-1.42",
doi = "10.18653/v1/2022.wanlp-1.42",
pages = "420--424",
abstract = "This study targets the shared task of Nuanced Arabic Dialect Identification (NADI) organized with the Workshop on Arabic Natural Language Processing (WANLP). It further focuses on Subtask 1 on the identification of the Arabic dialects at the country level. More specifically, it studies the impact of a traditional approach such as TF-IDF and then moves on to study the impact of advanced deep learning based methods. These methods include fully fine-tuning MARBERT as well as adapter based fine-tuning of MARBERT with and without performing data augmentation. The evaluation shows that the traditional approach based on TF-IDF scores the best in terms of accuracy on TEST-A dataset, while, the fine-tuned MARBERT with adapter on augmented data scores the second on Macro F1-score on the TEST-B dataset. This led to the proposed system being ranked second on the shared task on average.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shammary-etal-2022-tf">
<titleInfo>
<title>TF-IDF or Transformers for Arabic Dialect Identification? ITFLOWS participation in the NADI 2022 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fouad</namePart>
<namePart type="family">Shammary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zsolt</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Kardkovacs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehwish</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</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>This study targets the shared task of Nuanced Arabic Dialect Identification (NADI) organized with the Workshop on Arabic Natural Language Processing (WANLP). It further focuses on Subtask 1 on the identification of the Arabic dialects at the country level. More specifically, it studies the impact of a traditional approach such as TF-IDF and then moves on to study the impact of advanced deep learning based methods. These methods include fully fine-tuning MARBERT as well as adapter based fine-tuning of MARBERT with and without performing data augmentation. The evaluation shows that the traditional approach based on TF-IDF scores the best in terms of accuracy on TEST-A dataset, while, the fine-tuned MARBERT with adapter on augmented data scores the second on Macro F1-score on the TEST-B dataset. This led to the proposed system being ranked second on the shared task on average.</abstract>
<identifier type="citekey">shammary-etal-2022-tf</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.42</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.42</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>420</start>
<end>424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TF-IDF or Transformers for Arabic Dialect Identification? ITFLOWS participation in the NADI 2022 Shared Task
%A Shammary, Fouad
%A Chen, Yiyi
%A Kardkovacs, Zsolt T.
%A Alam, Mehwish
%A Afli, Haithem
%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 shammary-etal-2022-tf
%X This study targets the shared task of Nuanced Arabic Dialect Identification (NADI) organized with the Workshop on Arabic Natural Language Processing (WANLP). It further focuses on Subtask 1 on the identification of the Arabic dialects at the country level. More specifically, it studies the impact of a traditional approach such as TF-IDF and then moves on to study the impact of advanced deep learning based methods. These methods include fully fine-tuning MARBERT as well as adapter based fine-tuning of MARBERT with and without performing data augmentation. The evaluation shows that the traditional approach based on TF-IDF scores the best in terms of accuracy on TEST-A dataset, while, the fine-tuned MARBERT with adapter on augmented data scores the second on Macro F1-score on the TEST-B dataset. This led to the proposed system being ranked second on the shared task on average.
%R 10.18653/v1/2022.wanlp-1.42
%U https://aclanthology.org/2022.wanlp-1.42
%U https://doi.org/10.18653/v1/2022.wanlp-1.42
%P 420-424
Markdown (Informal)
[TF-IDF or Transformers for Arabic Dialect Identification? ITFLOWS participation in the NADI 2022 Shared Task](https://aclanthology.org/2022.wanlp-1.42) (Shammary et al., WANLP 2022)
ACL