@inproceedings{al-qurishi-etal-2022-aralegal,
title = "{A}ra{L}egal-{BERT}: A pretrained language model for {A}rabic Legal text",
author = "Al-qurishi, Muhammad and
Alqaseemi, Sarah and
Souissi, Riad",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nllp-1.31",
doi = "10.18653/v1/2022.nllp-1.31",
pages = "338--344",
abstract = "The effectiveness of the bidirectional encoder representations from transformers (BERT) model for multiple linguistic tasks is well documented. However, its potential for a narrow and specific domain, such as legal, has not been fully explored. In this study, we examine the use of BERT in the Arabic legal domain and customize this language model for several downstream tasks using different domain-relevant training and test datasets to train BERT from scratch. We introduce AraLegal-BERT, a bidirectional encoder transformer-based model that has been thoroughly tested and carefully optimized with the goal of amplifying the impact of natural language processing-driven solutions on jurisprudence, legal documents, and legal practice. We fine-tuned AraLegal-BERT and evaluated it against three BERT variants for the Arabic language in three natural language understanding tasks. The results showed that the base version of AraLegal-BERT achieved better accuracy than the typical and original BERT model concerning legal texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-qurishi-etal-2022-aralegal">
<titleInfo>
<title>AraLegal-BERT: A pretrained language model for Arabic Legal text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Al-qurishi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Alqaseemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riad</namePart>
<namePart type="family">Souissi</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 Natural Legal Language Processing Workshop 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</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>The effectiveness of the bidirectional encoder representations from transformers (BERT) model for multiple linguistic tasks is well documented. However, its potential for a narrow and specific domain, such as legal, has not been fully explored. In this study, we examine the use of BERT in the Arabic legal domain and customize this language model for several downstream tasks using different domain-relevant training and test datasets to train BERT from scratch. We introduce AraLegal-BERT, a bidirectional encoder transformer-based model that has been thoroughly tested and carefully optimized with the goal of amplifying the impact of natural language processing-driven solutions on jurisprudence, legal documents, and legal practice. We fine-tuned AraLegal-BERT and evaluated it against three BERT variants for the Arabic language in three natural language understanding tasks. The results showed that the base version of AraLegal-BERT achieved better accuracy than the typical and original BERT model concerning legal texts.</abstract>
<identifier type="citekey">al-qurishi-etal-2022-aralegal</identifier>
<identifier type="doi">10.18653/v1/2022.nllp-1.31</identifier>
<location>
<url>https://aclanthology.org/2022.nllp-1.31</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>338</start>
<end>344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AraLegal-BERT: A pretrained language model for Arabic Legal text
%A Al-qurishi, Muhammad
%A Alqaseemi, Sarah
%A Souissi, Riad
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%S Proceedings of the Natural Legal Language Processing Workshop 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F al-qurishi-etal-2022-aralegal
%X The effectiveness of the bidirectional encoder representations from transformers (BERT) model for multiple linguistic tasks is well documented. However, its potential for a narrow and specific domain, such as legal, has not been fully explored. In this study, we examine the use of BERT in the Arabic legal domain and customize this language model for several downstream tasks using different domain-relevant training and test datasets to train BERT from scratch. We introduce AraLegal-BERT, a bidirectional encoder transformer-based model that has been thoroughly tested and carefully optimized with the goal of amplifying the impact of natural language processing-driven solutions on jurisprudence, legal documents, and legal practice. We fine-tuned AraLegal-BERT and evaluated it against three BERT variants for the Arabic language in three natural language understanding tasks. The results showed that the base version of AraLegal-BERT achieved better accuracy than the typical and original BERT model concerning legal texts.
%R 10.18653/v1/2022.nllp-1.31
%U https://aclanthology.org/2022.nllp-1.31
%U https://doi.org/10.18653/v1/2022.nllp-1.31
%P 338-344
Markdown (Informal)
[AraLegal-BERT: A pretrained language model for Arabic Legal text](https://aclanthology.org/2022.nllp-1.31) (Al-qurishi et al., NLLP 2022)
ACL