@inproceedings{elmadany-etal-2023-orca,
title = "{ORCA}: A Challenging Benchmark for {A}rabic Language Understanding",
author = "Elmadany, AbdelRahim and
Nagoudi, ElMoatez Billah and
Abdul-Mageed, Muhammad",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.609",
doi = "10.18653/v1/2023.findings-acl.609",
pages = "9559--9586",
abstract = "Due to the crucial role pretrained language models play in modern NLP, several benchmarks have been proposed to evaluate their performance. In spite of these efforts, no public benchmark of diverse nature currently exists for evaluating Arabic NLU. This makes it challenging to measure progress for both Arabic and multilingual language models. This challenge is compounded by the fact that any benchmark targeting Arabic needs to take into account the fact that Arabic is not a single language but rather a collection of languages and language varieties. In this work, we introduce a publicly available benchmark for Arabic language understanding evaluation dubbed ORCA. It is carefully constructed to cover diverse Arabic varieties and a wide range of challenging Arabic understanding tasks exploiting 60 different datasets (across seven NLU task clusters). To measure current progress in Arabic NLU, we use ORCA to offer a comprehensive comparison between 18 multilingual and Arabic language models. We also provide a public leaderboard with a unified single-number evaluation metric (ORCA score) to facilitate future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elmadany-etal-2023-orca">
<titleInfo>
<title>ORCA: A Challenging Benchmark for Arabic Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ElMoatez</namePart>
<namePart type="given">Billah</namePart>
<namePart type="family">Nagoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Due to the crucial role pretrained language models play in modern NLP, several benchmarks have been proposed to evaluate their performance. In spite of these efforts, no public benchmark of diverse nature currently exists for evaluating Arabic NLU. This makes it challenging to measure progress for both Arabic and multilingual language models. This challenge is compounded by the fact that any benchmark targeting Arabic needs to take into account the fact that Arabic is not a single language but rather a collection of languages and language varieties. In this work, we introduce a publicly available benchmark for Arabic language understanding evaluation dubbed ORCA. It is carefully constructed to cover diverse Arabic varieties and a wide range of challenging Arabic understanding tasks exploiting 60 different datasets (across seven NLU task clusters). To measure current progress in Arabic NLU, we use ORCA to offer a comprehensive comparison between 18 multilingual and Arabic language models. We also provide a public leaderboard with a unified single-number evaluation metric (ORCA score) to facilitate future research.</abstract>
<identifier type="citekey">elmadany-etal-2023-orca</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.609</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.609</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>9559</start>
<end>9586</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ORCA: A Challenging Benchmark for Arabic Language Understanding
%A Elmadany, AbdelRahim
%A Nagoudi, ElMoatez Billah
%A Abdul-Mageed, Muhammad
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F elmadany-etal-2023-orca
%X Due to the crucial role pretrained language models play in modern NLP, several benchmarks have been proposed to evaluate their performance. In spite of these efforts, no public benchmark of diverse nature currently exists for evaluating Arabic NLU. This makes it challenging to measure progress for both Arabic and multilingual language models. This challenge is compounded by the fact that any benchmark targeting Arabic needs to take into account the fact that Arabic is not a single language but rather a collection of languages and language varieties. In this work, we introduce a publicly available benchmark for Arabic language understanding evaluation dubbed ORCA. It is carefully constructed to cover diverse Arabic varieties and a wide range of challenging Arabic understanding tasks exploiting 60 different datasets (across seven NLU task clusters). To measure current progress in Arabic NLU, we use ORCA to offer a comprehensive comparison between 18 multilingual and Arabic language models. We also provide a public leaderboard with a unified single-number evaluation metric (ORCA score) to facilitate future research.
%R 10.18653/v1/2023.findings-acl.609
%U https://aclanthology.org/2023.findings-acl.609
%U https://doi.org/10.18653/v1/2023.findings-acl.609
%P 9559-9586
Markdown (Informal)
[ORCA: A Challenging Benchmark for Arabic Language Understanding](https://aclanthology.org/2023.findings-acl.609) (Elmadany et al., Findings 2023)
ACL