@inproceedings{ghaddar-etal-2022-revisiting,
title = "Revisiting Pre-trained Language Models and their Evaluation for {A}rabic Natural Language Processing",
author = "Ghaddar, Abbas and
Wu, Yimeng and
Bagga, Sunyam and
Rashid, Ahmad and
Bibi, Khalil and
Rezagholizadeh, Mehdi and
Xing, Chao and
Wang, Yasheng and
Duan, Xinyu and
Wang, Zhefeng and
Huai, Baoxing and
Jiang, Xin and
Liu, Qun and
Langlais, Phillippe",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.205",
doi = "10.18653/v1/2022.emnlp-main.205",
pages = "3135--3151",
abstract = "There is a growing body of work in recent years to develop pre-trained language models (PLMs) for the Arabic language. This work addresses two major problems in existing Arabic PLMs that limit the progress of the Arabic NLU and NLG fields. First, existing Arabic PLMs are not well-explored and their pre-training can be improved significantly using a more methodical approach. Second, there is a lack of systematic and reproducible evaluation of these models in the literature. We revisit both the pre-training and evaluation of Arabic PLMs. In terms of pre-training, we explore the impact of the quality of the pretraining data, the size of the model, and the incorporation of character-level information on Arabic PLM. As a result, we release three new Arabic BERT-style models ( JABER, Char-JABER, and SABER), and two T5-style models (AT5S and AT5B). In terms of evaluation, we conduct a comprehensive empirical study to systematically evaluate the performance of existing state-of-the-art models on ALUE, a leaderboard-powered benchmark for Arabic NLU tasks, and on a subset of the Arabic generative tasks. We show that our models significantly outperform existing Arabic PLMs and achieve a new state-of-the-art performance on discriminative and generative Arabic NLU and NLG tasks. Our models and source code to reproduce results will be made available upon acceptance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghaddar-etal-2022-revisiting">
<titleInfo>
<title>Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abbas</namePart>
<namePart type="family">Ghaddar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yimeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunyam</namePart>
<namePart type="family">Bagga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Bibi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehdi</namePart>
<namePart type="family">Rezagholizadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhefeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoxing</namePart>
<namePart type="family">Huai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phillippe</namePart>
<namePart type="family">Langlais</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 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is a growing body of work in recent years to develop pre-trained language models (PLMs) for the Arabic language. This work addresses two major problems in existing Arabic PLMs that limit the progress of the Arabic NLU and NLG fields. First, existing Arabic PLMs are not well-explored and their pre-training can be improved significantly using a more methodical approach. Second, there is a lack of systematic and reproducible evaluation of these models in the literature. We revisit both the pre-training and evaluation of Arabic PLMs. In terms of pre-training, we explore the impact of the quality of the pretraining data, the size of the model, and the incorporation of character-level information on Arabic PLM. As a result, we release three new Arabic BERT-style models ( JABER, Char-JABER, and SABER), and two T5-style models (AT5S and AT5B). In terms of evaluation, we conduct a comprehensive empirical study to systematically evaluate the performance of existing state-of-the-art models on ALUE, a leaderboard-powered benchmark for Arabic NLU tasks, and on a subset of the Arabic generative tasks. We show that our models significantly outperform existing Arabic PLMs and achieve a new state-of-the-art performance on discriminative and generative Arabic NLU and NLG tasks. Our models and source code to reproduce results will be made available upon acceptance.</abstract>
<identifier type="citekey">ghaddar-etal-2022-revisiting</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.205</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.205</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3135</start>
<end>3151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing
%A Ghaddar, Abbas
%A Wu, Yimeng
%A Bagga, Sunyam
%A Rashid, Ahmad
%A Bibi, Khalil
%A Rezagholizadeh, Mehdi
%A Xing, Chao
%A Wang, Yasheng
%A Duan, Xinyu
%A Wang, Zhefeng
%A Huai, Baoxing
%A Jiang, Xin
%A Liu, Qun
%A Langlais, Phillippe
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F ghaddar-etal-2022-revisiting
%X There is a growing body of work in recent years to develop pre-trained language models (PLMs) for the Arabic language. This work addresses two major problems in existing Arabic PLMs that limit the progress of the Arabic NLU and NLG fields. First, existing Arabic PLMs are not well-explored and their pre-training can be improved significantly using a more methodical approach. Second, there is a lack of systematic and reproducible evaluation of these models in the literature. We revisit both the pre-training and evaluation of Arabic PLMs. In terms of pre-training, we explore the impact of the quality of the pretraining data, the size of the model, and the incorporation of character-level information on Arabic PLM. As a result, we release three new Arabic BERT-style models ( JABER, Char-JABER, and SABER), and two T5-style models (AT5S and AT5B). In terms of evaluation, we conduct a comprehensive empirical study to systematically evaluate the performance of existing state-of-the-art models on ALUE, a leaderboard-powered benchmark for Arabic NLU tasks, and on a subset of the Arabic generative tasks. We show that our models significantly outperform existing Arabic PLMs and achieve a new state-of-the-art performance on discriminative and generative Arabic NLU and NLG tasks. Our models and source code to reproduce results will be made available upon acceptance.
%R 10.18653/v1/2022.emnlp-main.205
%U https://aclanthology.org/2022.emnlp-main.205
%U https://doi.org/10.18653/v1/2022.emnlp-main.205
%P 3135-3151
Markdown (Informal)
[Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing](https://aclanthology.org/2022.emnlp-main.205) (Ghaddar et al., EMNLP 2022)
ACL
- Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, and Phillippe Langlais. 2022. Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3135–3151, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.