@inproceedings{alsarra-etal-2023-conflibert,
title = "{C}onfli{BERT}-{A}rabic: A Pre-trained {A}rabic Language Model for Politics, Conflicts and Violence",
author = "Alsarra, Sultan and
Abdeljaber, Luay and
Yang, Wooseong and
Zawad, Niamat and
Khan, Latifur and
Brandt, Patrick and
Osorio, Javier and
D{'}Orazio, Vito",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.11",
pages = "98--108",
abstract = "This study investigates the use of Natural Language Processing (NLP) methods to analyze politics, conflicts and violence in the Middle East using domain-specific pre-trained language models. We introduce Arabic text and present ConfliBERT-Arabic, a pre-trained language models that can efficiently analyze political, conflict and violence-related texts. Our technique hones a pre-trained model using a corpus of Arabic texts about regional politics and conflicts. Performance of our models is compared to baseline BERT models. Our findings show that the performance of NLP models for Middle Eastern politics and conflict analysis are enhanced by the use of domain-specific pre-trained local language models. This study offers political and conflict analysts, including policymakers, scholars, and practitioners new approaches and tools for deciphering the intricate dynamics of local politics and conflicts directly in Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alsarra-etal-2023-conflibert">
<titleInfo>
<title>ConfliBERT-Arabic: A Pre-trained Arabic Language Model for Politics, Conflicts and Violence</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sultan</namePart>
<namePart type="family">Alsarra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luay</namePart>
<namePart type="family">Abdeljaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wooseong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niamat</namePart>
<namePart type="family">Zawad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Latifur</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Brandt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Osorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vito</namePart>
<namePart type="family">D’Orazio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study investigates the use of Natural Language Processing (NLP) methods to analyze politics, conflicts and violence in the Middle East using domain-specific pre-trained language models. We introduce Arabic text and present ConfliBERT-Arabic, a pre-trained language models that can efficiently analyze political, conflict and violence-related texts. Our technique hones a pre-trained model using a corpus of Arabic texts about regional politics and conflicts. Performance of our models is compared to baseline BERT models. Our findings show that the performance of NLP models for Middle Eastern politics and conflict analysis are enhanced by the use of domain-specific pre-trained local language models. This study offers political and conflict analysts, including policymakers, scholars, and practitioners new approaches and tools for deciphering the intricate dynamics of local politics and conflicts directly in Arabic.</abstract>
<identifier type="citekey">alsarra-etal-2023-conflibert</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.11</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>98</start>
<end>108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConfliBERT-Arabic: A Pre-trained Arabic Language Model for Politics, Conflicts and Violence
%A Alsarra, Sultan
%A Abdeljaber, Luay
%A Yang, Wooseong
%A Zawad, Niamat
%A Khan, Latifur
%A Brandt, Patrick
%A Osorio, Javier
%A D’Orazio, Vito
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F alsarra-etal-2023-conflibert
%X This study investigates the use of Natural Language Processing (NLP) methods to analyze politics, conflicts and violence in the Middle East using domain-specific pre-trained language models. We introduce Arabic text and present ConfliBERT-Arabic, a pre-trained language models that can efficiently analyze political, conflict and violence-related texts. Our technique hones a pre-trained model using a corpus of Arabic texts about regional politics and conflicts. Performance of our models is compared to baseline BERT models. Our findings show that the performance of NLP models for Middle Eastern politics and conflict analysis are enhanced by the use of domain-specific pre-trained local language models. This study offers political and conflict analysts, including policymakers, scholars, and practitioners new approaches and tools for deciphering the intricate dynamics of local politics and conflicts directly in Arabic.
%U https://aclanthology.org/2023.ranlp-1.11
%P 98-108
Markdown (Informal)
[ConfliBERT-Arabic: A Pre-trained Arabic Language Model for Politics, Conflicts and Violence](https://aclanthology.org/2023.ranlp-1.11) (Alsarra et al., RANLP 2023)
ACL
- Sultan Alsarra, Luay Abdeljaber, Wooseong Yang, Niamat Zawad, Latifur Khan, Patrick Brandt, Javier Osorio, and Vito D’Orazio. 2023. ConfliBERT-Arabic: A Pre-trained Arabic Language Model for Politics, Conflicts and Violence. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 98–108, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.