@inproceedings{alrajhi-etal-2022-assessing,
title = "Assessing the Linguistic Knowledge in {A}rabic Pre-trained Language Models Using Minimal Pairs",
author = "Alrajhi, Wafa Abdullah and
Al-Khalifa, Hend and
AlSalman, Abdulmalik",
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-1.17",
doi = "10.18653/v1/2022.wanlp-1.17",
pages = "185--193",
abstract = "Despite the noticeable progress that we recently witnessed in Arabic pre-trained language models (PLMs), the linguistic knowledge captured by these models remains unclear. In this paper, we conducted a study to evaluate available Arabic PLMs in terms of their linguistic knowledge. BERT-based language models (LMs) are evaluated using Minimum Pairs (MP), where each pair represents a grammatical sentence and its contradictory counterpart. MPs isolate specific linguistic knowledge to test the model{'}s sensitivity in understanding a specific linguistic phenomenon. We cover nine major Arabic phenomena: Verbal sentences, Nominal sentences, Adjective Modification, and Idafa construction. The experiments compared the results of fifteen Arabic BERT-based PLMs. Overall, among all tested models, CAMeL-CA outperformed the other PLMs by achieving the highest overall accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alrajhi-etal-2022-assessing">
<titleInfo>
<title>Assessing the Linguistic Knowledge in Arabic Pre-trained Language Models Using Minimal Pairs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wafa</namePart>
<namePart type="given">Abdullah</namePart>
<namePart type="family">Alrajhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulmalik</namePart>
<namePart type="family">AlSalman</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>Despite the noticeable progress that we recently witnessed in Arabic pre-trained language models (PLMs), the linguistic knowledge captured by these models remains unclear. In this paper, we conducted a study to evaluate available Arabic PLMs in terms of their linguistic knowledge. BERT-based language models (LMs) are evaluated using Minimum Pairs (MP), where each pair represents a grammatical sentence and its contradictory counterpart. MPs isolate specific linguistic knowledge to test the model’s sensitivity in understanding a specific linguistic phenomenon. We cover nine major Arabic phenomena: Verbal sentences, Nominal sentences, Adjective Modification, and Idafa construction. The experiments compared the results of fifteen Arabic BERT-based PLMs. Overall, among all tested models, CAMeL-CA outperformed the other PLMs by achieving the highest overall accuracy.</abstract>
<identifier type="citekey">alrajhi-etal-2022-assessing</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.17</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.17</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>185</start>
<end>193</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing the Linguistic Knowledge in Arabic Pre-trained Language Models Using Minimal Pairs
%A Alrajhi, Wafa Abdullah
%A Al-Khalifa, Hend
%A AlSalman, Abdulmalik
%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 alrajhi-etal-2022-assessing
%X Despite the noticeable progress that we recently witnessed in Arabic pre-trained language models (PLMs), the linguistic knowledge captured by these models remains unclear. In this paper, we conducted a study to evaluate available Arabic PLMs in terms of their linguistic knowledge. BERT-based language models (LMs) are evaluated using Minimum Pairs (MP), where each pair represents a grammatical sentence and its contradictory counterpart. MPs isolate specific linguistic knowledge to test the model’s sensitivity in understanding a specific linguistic phenomenon. We cover nine major Arabic phenomena: Verbal sentences, Nominal sentences, Adjective Modification, and Idafa construction. The experiments compared the results of fifteen Arabic BERT-based PLMs. Overall, among all tested models, CAMeL-CA outperformed the other PLMs by achieving the highest overall accuracy.
%R 10.18653/v1/2022.wanlp-1.17
%U https://aclanthology.org/2022.wanlp-1.17
%U https://doi.org/10.18653/v1/2022.wanlp-1.17
%P 185-193
Markdown (Informal)
[Assessing the Linguistic Knowledge in Arabic Pre-trained Language Models Using Minimal Pairs](https://aclanthology.org/2022.wanlp-1.17) (Alrajhi et al., WANLP 2022)
ACL