@inproceedings{aftiss-etal-2025-empirical,
title = "Empirical Evaluation of Pre-trained Language Models for Summarizing {M}oroccan {D}arija News Articles",
author = "Aftiss, Azzedine and
Lamsiyah, Salima and
Schommer, Christoph and
El Alaoui, Said Ouatik",
editor = "Ezzini, Saad and
Alami, Hamza and
Berrada, Ismail and
Benlahbib, Abdessamad and
El Mahdaouy, Abdelkader and
Lamsiyah, Salima and
Derrouz, Hatim and
Haddad Haddad, Amal and
Jarrar, Mustafa and
El-Haj, Mo and
Mitkov, Ruslan and
Rayson, Paul",
booktitle = "Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wacl-1.9/",
pages = "77--85",
abstract = "Moroccan Dialect (MD), or {\textquotedblleft}Darija,{\textquotedblright} is a primary spoken variant of Arabic in Morocco, yet remains underrepresented in Natural Language Processing (NLP) research, particularly in tasks like summarization. Despite a growing volume of MD textual data online, there is a lack of robust resources and NLP models tailored to handle the unique linguistic challenges posed by MD. In response, we introduce .MA{\_}v2, an expanded version of the GOUD.MA dataset, containing over 50k articles with their titles across 11 categories. This dataset provides a more comprehensive resource for developing summarization models. We evaluate the application of large language models (LLMs) for MD summarization, utilizing both fine-tuning and zero-shot prompting with encoder-decoder and causal LLMs, respectively. Our findings demonstrate that an expanded dataset improves summarization performance and highlights the capabilities of recent LLMs in handling MD text. We open-source our dataset, fine-tuned models, and all experimental code, establishing a foundation for future advancements in MD NLP. We release the code at https://github.com/AzzedineAftiss/Moroccan-Dialect-Summarization."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aftiss-etal-2025-empirical">
<titleInfo>
<title>Empirical Evaluation of Pre-trained Language Models for Summarizing Moroccan Darija News Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Azzedine</namePart>
<namePart type="family">Aftiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Lamsiyah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Schommer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Said</namePart>
<namePart type="given">Ouatik</namePart>
<namePart type="family">El Alaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamza</namePart>
<namePart type="family">Alami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismail</namePart>
<namePart type="family">Berrada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdessamad</namePart>
<namePart type="family">Benlahbib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelkader</namePart>
<namePart type="family">El Mahdaouy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Lamsiyah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatim</namePart>
<namePart type="family">Derrouz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Haddad Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Moroccan Dialect (MD), or “Darija,” is a primary spoken variant of Arabic in Morocco, yet remains underrepresented in Natural Language Processing (NLP) research, particularly in tasks like summarization. Despite a growing volume of MD textual data online, there is a lack of robust resources and NLP models tailored to handle the unique linguistic challenges posed by MD. In response, we introduce .MA_v2, an expanded version of the GOUD.MA dataset, containing over 50k articles with their titles across 11 categories. This dataset provides a more comprehensive resource for developing summarization models. We evaluate the application of large language models (LLMs) for MD summarization, utilizing both fine-tuning and zero-shot prompting with encoder-decoder and causal LLMs, respectively. Our findings demonstrate that an expanded dataset improves summarization performance and highlights the capabilities of recent LLMs in handling MD text. We open-source our dataset, fine-tuned models, and all experimental code, establishing a foundation for future advancements in MD NLP. We release the code at https://github.com/AzzedineAftiss/Moroccan-Dialect-Summarization.</abstract>
<identifier type="citekey">aftiss-etal-2025-empirical</identifier>
<location>
<url>https://aclanthology.org/2025.wacl-1.9/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>77</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Empirical Evaluation of Pre-trained Language Models for Summarizing Moroccan Darija News Articles
%A Aftiss, Azzedine
%A Lamsiyah, Salima
%A Schommer, Christoph
%A El Alaoui, Said Ouatik
%Y Ezzini, Saad
%Y Alami, Hamza
%Y Berrada, Ismail
%Y Benlahbib, Abdessamad
%Y El Mahdaouy, Abdelkader
%Y Lamsiyah, Salima
%Y Derrouz, Hatim
%Y Haddad Haddad, Amal
%Y Jarrar, Mustafa
%Y El-Haj, Mo
%Y Mitkov, Ruslan
%Y Rayson, Paul
%S Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F aftiss-etal-2025-empirical
%X Moroccan Dialect (MD), or “Darija,” is a primary spoken variant of Arabic in Morocco, yet remains underrepresented in Natural Language Processing (NLP) research, particularly in tasks like summarization. Despite a growing volume of MD textual data online, there is a lack of robust resources and NLP models tailored to handle the unique linguistic challenges posed by MD. In response, we introduce .MA_v2, an expanded version of the GOUD.MA dataset, containing over 50k articles with their titles across 11 categories. This dataset provides a more comprehensive resource for developing summarization models. We evaluate the application of large language models (LLMs) for MD summarization, utilizing both fine-tuning and zero-shot prompting with encoder-decoder and causal LLMs, respectively. Our findings demonstrate that an expanded dataset improves summarization performance and highlights the capabilities of recent LLMs in handling MD text. We open-source our dataset, fine-tuned models, and all experimental code, establishing a foundation for future advancements in MD NLP. We release the code at https://github.com/AzzedineAftiss/Moroccan-Dialect-Summarization.
%U https://aclanthology.org/2025.wacl-1.9/
%P 77-85
Markdown (Informal)
[Empirical Evaluation of Pre-trained Language Models for Summarizing Moroccan Darija News Articles](https://aclanthology.org/2025.wacl-1.9/) (Aftiss et al., WACL 2025)
ACL