@inproceedings{khader-etal-2024-munazarat,
title = "Munazarat 1.0: A Corpus of {A}rabic Competitive Debates",
author = "Khader, Mohammad M. and
Al-Sharafi, AbdulGabbar and
Al-Sioufy, Mohamad Hamza and
Zaghouani, Wajdi and
Al-Zawqari, Ali",
editor = "Al-Khalifa, Hend and
Darwish, Kareem and
Mubarak, Hamdy and
Ali, Mona and
Elsayed, Tamer",
booktitle = "Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.osact-1.3",
pages = "20--30",
abstract = "This paper introduces the Corpus of Arabic Competitive Debates (Munazarat). Despite the significance of competitive debating as an activity of fostering critical thinking and promoting dialogue, researchers within the fields of Arabic Natural Language Processing (NLP), linguistics, argumentation studies, and education have access to very limited datasets about competitive debating. At this study stage, we introduce Munazarat 1.0, which combines recordings of approximately 50 hours collected from 73 debates at QatarDebate-recognized tournaments, where all of those debates were available on YouTube. Munazarat is a novel specialized speech Arabic corpus, mostly in Modern Standard Arabic (MSA), consisting of diverse debating topics and showing rich metadata for each debate. The transcription of debates was done using Fenek, a speech-to-text Kanari AI tool, and three native Arabic speakers reviewed each transcription file to enhance the quality provided by the machine. The Munazarat 1.0 dataset can be used to train Arabic NLP tools, develop an argumentation mining machine, and analyze Arabic argumentation and rhetoric styles. Keywords: Arabic Speech Corpus, Modern Standard Arabic, Debates",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khader-etal-2024-munazarat">
<titleInfo>
<title>Munazarat 1.0: A Corpus of Arabic Competitive Debates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Khader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdulGabbar</namePart>
<namePart type="family">Al-Sharafi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamad</namePart>
<namePart type="given">Hamza</namePart>
<namePart type="family">Al-Sioufy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Al-Zawqari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024</title>
</titleInfo>
<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">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces the Corpus of Arabic Competitive Debates (Munazarat). Despite the significance of competitive debating as an activity of fostering critical thinking and promoting dialogue, researchers within the fields of Arabic Natural Language Processing (NLP), linguistics, argumentation studies, and education have access to very limited datasets about competitive debating. At this study stage, we introduce Munazarat 1.0, which combines recordings of approximately 50 hours collected from 73 debates at QatarDebate-recognized tournaments, where all of those debates were available on YouTube. Munazarat is a novel specialized speech Arabic corpus, mostly in Modern Standard Arabic (MSA), consisting of diverse debating topics and showing rich metadata for each debate. The transcription of debates was done using Fenek, a speech-to-text Kanari AI tool, and three native Arabic speakers reviewed each transcription file to enhance the quality provided by the machine. The Munazarat 1.0 dataset can be used to train Arabic NLP tools, develop an argumentation mining machine, and analyze Arabic argumentation and rhetoric styles. Keywords: Arabic Speech Corpus, Modern Standard Arabic, Debates</abstract>
<identifier type="citekey">khader-etal-2024-munazarat</identifier>
<location>
<url>https://aclanthology.org/2024.osact-1.3</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>20</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Munazarat 1.0: A Corpus of Arabic Competitive Debates
%A Khader, Mohammad M.
%A Al-Sharafi, AbdulGabbar
%A Al-Sioufy, Mohamad Hamza
%A Zaghouani, Wajdi
%A Al-Zawqari, Ali
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Mubarak, Hamdy
%Y Ali, Mona
%Y Elsayed, Tamer
%S Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F khader-etal-2024-munazarat
%X This paper introduces the Corpus of Arabic Competitive Debates (Munazarat). Despite the significance of competitive debating as an activity of fostering critical thinking and promoting dialogue, researchers within the fields of Arabic Natural Language Processing (NLP), linguistics, argumentation studies, and education have access to very limited datasets about competitive debating. At this study stage, we introduce Munazarat 1.0, which combines recordings of approximately 50 hours collected from 73 debates at QatarDebate-recognized tournaments, where all of those debates were available on YouTube. Munazarat is a novel specialized speech Arabic corpus, mostly in Modern Standard Arabic (MSA), consisting of diverse debating topics and showing rich metadata for each debate. The transcription of debates was done using Fenek, a speech-to-text Kanari AI tool, and three native Arabic speakers reviewed each transcription file to enhance the quality provided by the machine. The Munazarat 1.0 dataset can be used to train Arabic NLP tools, develop an argumentation mining machine, and analyze Arabic argumentation and rhetoric styles. Keywords: Arabic Speech Corpus, Modern Standard Arabic, Debates
%U https://aclanthology.org/2024.osact-1.3
%P 20-30
Markdown (Informal)
[Munazarat 1.0: A Corpus of Arabic Competitive Debates](https://aclanthology.org/2024.osact-1.3) (Khader et al., OSACT-WS 2024)
ACL
- Mohammad M. Khader, AbdulGabbar Al-Sharafi, Mohamad Hamza Al-Sioufy, Wajdi Zaghouani, and Ali Al-Zawqari. 2024. Munazarat 1.0: A Corpus of Arabic Competitive Debates. In Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024, pages 20–30, Torino, Italia. ELRA and ICCL.