@inproceedings{yusuf-etal-2022-arabic,
title = "{A}rabic Dialect Identification with a Few Labeled Examples Using Generative Adversarial Networks",
author = "Yusuf, Mahmoud and
Torki, Marwan and
El-Makky, Nagwa",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-main.16",
pages = "196--204",
abstract = "Given the challenges and complexities introduced while dealing with Dialect Arabic (DA) variations, Transformer based models, e.g., BERT, outperformed other models in dealing with the DA identification task. However, to fine-tune these models, a large corpus is required. Getting a large number high quality labeled examples for some Dialect Arabic classes is challenging and time-consuming. In this paper, we address the Dialect Arabic Identification task. We extend the transformer-based models, ARBERT and MARBERT, with unlabeled data in a generative adversarial setting using Semi-Supervised Generative Adversarial Networks (SS-GAN). Our model enabled producing high-quality embeddings for the Dialect Arabic examples and aided the model to better generalize for the downstream classification task given few labeled examples. Experimental results showed that our model reached better performance and faster convergence when only a few labeled examples are available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yusuf-etal-2022-arabic">
<titleInfo>
<title>Arabic Dialect Identification with a Few Labeled Examples Using Generative Adversarial Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Yusuf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwan</namePart>
<namePart type="family">Torki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nagwa</namePart>
<namePart type="family">El-Makky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Given the challenges and complexities introduced while dealing with Dialect Arabic (DA) variations, Transformer based models, e.g., BERT, outperformed other models in dealing with the DA identification task. However, to fine-tune these models, a large corpus is required. Getting a large number high quality labeled examples for some Dialect Arabic classes is challenging and time-consuming. In this paper, we address the Dialect Arabic Identification task. We extend the transformer-based models, ARBERT and MARBERT, with unlabeled data in a generative adversarial setting using Semi-Supervised Generative Adversarial Networks (SS-GAN). Our model enabled producing high-quality embeddings for the Dialect Arabic examples and aided the model to better generalize for the downstream classification task given few labeled examples. Experimental results showed that our model reached better performance and faster convergence when only a few labeled examples are available.</abstract>
<identifier type="citekey">yusuf-etal-2022-arabic</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-main.16</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>196</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Dialect Identification with a Few Labeled Examples Using Generative Adversarial Networks
%A Yusuf, Mahmoud
%A Torki, Marwan
%A El-Makky, Nagwa
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F yusuf-etal-2022-arabic
%X Given the challenges and complexities introduced while dealing with Dialect Arabic (DA) variations, Transformer based models, e.g., BERT, outperformed other models in dealing with the DA identification task. However, to fine-tune these models, a large corpus is required. Getting a large number high quality labeled examples for some Dialect Arabic classes is challenging and time-consuming. In this paper, we address the Dialect Arabic Identification task. We extend the transformer-based models, ARBERT and MARBERT, with unlabeled data in a generative adversarial setting using Semi-Supervised Generative Adversarial Networks (SS-GAN). Our model enabled producing high-quality embeddings for the Dialect Arabic examples and aided the model to better generalize for the downstream classification task given few labeled examples. Experimental results showed that our model reached better performance and faster convergence when only a few labeled examples are available.
%U https://aclanthology.org/2022.aacl-main.16
%P 196-204
Markdown (Informal)
[Arabic Dialect Identification with a Few Labeled Examples Using Generative Adversarial Networks](https://aclanthology.org/2022.aacl-main.16) (Yusuf et al., AACL-IJCNLP 2022)
ACL