@inproceedings{israeli-etal-2024-diaset,
title = "{D}ia{S}et: An Annotated Dataset of {A}rabic Conversations",
author = "Israeli, Abraham and
Naaman, Aviv and
Maduel, Guy and
Makhoul, Rawaa and
Qaraeen, Dana and
Ejmail, Amir and
Lisnanskey, Dina and
Jubran, Julian and
Fine, Shai and
Bar, Kfir",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.436/",
pages = "4865--4876",
abstract = "We introduce DiaSet, a novel dataset of dialectical Arabic speech, manually transcribed and annotated for two specific downstream tasks: sentiment analysis and named entity recognition. The dataset encapsulates the Palestine dialect, predominantly spoken in Palestine, Israel, and Jordan. Our dataset incorporates authentic conversations between YouTube influencers and their respective guests. Furthermore, we have enriched the dataset with simulated conversations initiated by inviting participants from various locales within the said regions. The participants were encouraged to engage in dialogues with our interviewer. Overall, DiaSet consists of 644.8K tokens and 23.2K annotated instances. Uniform writing standards were upheld during the transcription process. Additionally, we established baseline models by leveraging some of the pre-existing Arabic BERT language models, showcasing the potential applications and efficiencies of our dataset. We make DiaSet publicly available for further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="israeli-etal-2024-diaset">
<titleInfo>
<title>DiaSet: An Annotated Dataset of Arabic Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abraham</namePart>
<namePart type="family">Israeli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aviv</namePart>
<namePart type="family">Naaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Maduel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawaa</namePart>
<namePart type="family">Makhoul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Qaraeen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Ejmail</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Lisnanskey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Jubran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Fine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>We introduce DiaSet, a novel dataset of dialectical Arabic speech, manually transcribed and annotated for two specific downstream tasks: sentiment analysis and named entity recognition. The dataset encapsulates the Palestine dialect, predominantly spoken in Palestine, Israel, and Jordan. Our dataset incorporates authentic conversations between YouTube influencers and their respective guests. Furthermore, we have enriched the dataset with simulated conversations initiated by inviting participants from various locales within the said regions. The participants were encouraged to engage in dialogues with our interviewer. Overall, DiaSet consists of 644.8K tokens and 23.2K annotated instances. Uniform writing standards were upheld during the transcription process. Additionally, we established baseline models by leveraging some of the pre-existing Arabic BERT language models, showcasing the potential applications and efficiencies of our dataset. We make DiaSet publicly available for further research.</abstract>
<identifier type="citekey">israeli-etal-2024-diaset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.436/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4865</start>
<end>4876</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiaSet: An Annotated Dataset of Arabic Conversations
%A Israeli, Abraham
%A Naaman, Aviv
%A Maduel, Guy
%A Makhoul, Rawaa
%A Qaraeen, Dana
%A Ejmail, Amir
%A Lisnanskey, Dina
%A Jubran, Julian
%A Fine, Shai
%A Bar, Kfir
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F israeli-etal-2024-diaset
%X We introduce DiaSet, a novel dataset of dialectical Arabic speech, manually transcribed and annotated for two specific downstream tasks: sentiment analysis and named entity recognition. The dataset encapsulates the Palestine dialect, predominantly spoken in Palestine, Israel, and Jordan. Our dataset incorporates authentic conversations between YouTube influencers and their respective guests. Furthermore, we have enriched the dataset with simulated conversations initiated by inviting participants from various locales within the said regions. The participants were encouraged to engage in dialogues with our interviewer. Overall, DiaSet consists of 644.8K tokens and 23.2K annotated instances. Uniform writing standards were upheld during the transcription process. Additionally, we established baseline models by leveraging some of the pre-existing Arabic BERT language models, showcasing the potential applications and efficiencies of our dataset. We make DiaSet publicly available for further research.
%U https://aclanthology.org/2024.lrec-main.436/
%P 4865-4876
Markdown (Informal)
[DiaSet: An Annotated Dataset of Arabic Conversations](https://aclanthology.org/2024.lrec-main.436/) (Israeli et al., LREC-COLING 2024)
ACL
- Abraham Israeli, Aviv Naaman, Guy Maduel, Rawaa Makhoul, Dana Qaraeen, Amir Ejmail, Dina Lisnanskey, Julian Jubran, Shai Fine, and Kfir Bar. 2024. DiaSet: An Annotated Dataset of Arabic Conversations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4865–4876, Torino, Italia. ELRA and ICCL.