@inproceedings{nagoudi-etal-2023-dolphin,
title = "Dolphin: A Challenging and Diverse Benchmark for {A}rabic {NLG}",
author = "Nagoudi, El Moatez Billah and
Elmadany, AbdelRahim and
El-Shangiti, Ahmed and
Abdul-Mageed, Muhammad",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.98",
doi = "10.18653/v1/2023.findings-emnlp.98",
pages = "1404--1422",
abstract = "We present Dolphin, a novel benchmark that addresses the need for a natural language generation (NLG) evaluation framework dedicated to the wide collection of Arabic languages and varieties. The proposed benchmark encompasses a broad range of 13 different NLG tasks, including dialogue generation, question answering, machine translation, summarization, among others. Dolphin comprises a substantial corpus of 40 diverse and representative public datasets across 50 test splits, carefully curated to reflect real-world scenarios and the linguistic richness of Arabic. It sets a new standard for evaluating the performance and generalization capabilities of Arabic and multilingual models, promising to enable researchers to push the boundaries of current methodologies. We provide an extensive analysis of Dolphin, highlighting its diversity and identifying gaps in current Arabic NLG research. We also offer a public leaderboard that is both interactive and modular and evaluate several Arabic and multilingual models on our benchmark, allowing us to set strong baselines against which researchers can compare.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nagoudi-etal-2023-dolphin">
<titleInfo>
<title>Dolphin: A Challenging and Diverse Benchmark for Arabic NLG</title>
</titleInfo>
<name type="personal">
<namePart type="given">El</namePart>
<namePart type="given">Moatez</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">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">El-Shangiti</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>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Dolphin, a novel benchmark that addresses the need for a natural language generation (NLG) evaluation framework dedicated to the wide collection of Arabic languages and varieties. The proposed benchmark encompasses a broad range of 13 different NLG tasks, including dialogue generation, question answering, machine translation, summarization, among others. Dolphin comprises a substantial corpus of 40 diverse and representative public datasets across 50 test splits, carefully curated to reflect real-world scenarios and the linguistic richness of Arabic. It sets a new standard for evaluating the performance and generalization capabilities of Arabic and multilingual models, promising to enable researchers to push the boundaries of current methodologies. We provide an extensive analysis of Dolphin, highlighting its diversity and identifying gaps in current Arabic NLG research. We also offer a public leaderboard that is both interactive and modular and evaluate several Arabic and multilingual models on our benchmark, allowing us to set strong baselines against which researchers can compare.</abstract>
<identifier type="citekey">nagoudi-etal-2023-dolphin</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.98</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.98</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>1404</start>
<end>1422</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dolphin: A Challenging and Diverse Benchmark for Arabic NLG
%A Nagoudi, El Moatez Billah
%A Elmadany, AbdelRahim
%A El-Shangiti, Ahmed
%A Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F nagoudi-etal-2023-dolphin
%X We present Dolphin, a novel benchmark that addresses the need for a natural language generation (NLG) evaluation framework dedicated to the wide collection of Arabic languages and varieties. The proposed benchmark encompasses a broad range of 13 different NLG tasks, including dialogue generation, question answering, machine translation, summarization, among others. Dolphin comprises a substantial corpus of 40 diverse and representative public datasets across 50 test splits, carefully curated to reflect real-world scenarios and the linguistic richness of Arabic. It sets a new standard for evaluating the performance and generalization capabilities of Arabic and multilingual models, promising to enable researchers to push the boundaries of current methodologies. We provide an extensive analysis of Dolphin, highlighting its diversity and identifying gaps in current Arabic NLG research. We also offer a public leaderboard that is both interactive and modular and evaluate several Arabic and multilingual models on our benchmark, allowing us to set strong baselines against which researchers can compare.
%R 10.18653/v1/2023.findings-emnlp.98
%U https://aclanthology.org/2023.findings-emnlp.98
%U https://doi.org/10.18653/v1/2023.findings-emnlp.98
%P 1404-1422
Markdown (Informal)
[Dolphin: A Challenging and Diverse Benchmark for Arabic NLG](https://aclanthology.org/2023.findings-emnlp.98) (Nagoudi et al., Findings 2023)
ACL
- El Moatez Billah Nagoudi, AbdelRahim Elmadany, Ahmed El-Shangiti, and Muhammad Abdul-Mageed. 2023. Dolphin: A Challenging and Diverse Benchmark for Arabic NLG. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1404–1422, Singapore. Association for Computational Linguistics.