AbjadNLP Archive · First Edition

AbjadNLP 2025The 1st Workshop on NLP for Languages Using Arabic Script

The inaugural AbjadNLP workshop brought together researchers working on Arabic, Perso-Arabic and Ajami languages, creating a dedicated forum for language technology across one of the world's most widely used script traditions.

1stedition of AbjadNLP
15accepted papers listed
~1Bspeakers across the wider language scope
43+Ajami languages highlighted in the original call
Why AbjadNLP

A dedicated home for Arabic-script language technology

AbjadNLP was established to advance Natural Language Processing for languages that use Arabic-derived writing systems. The first edition deliberately reached beyond Arabic to include Perso-Arabic and Ajami traditions, creating a shared research space for languages that face related challenges in orthography, digital resources, representation and tooling.

The workshop focused on the linguistic structures, resources and technical challenges of these languages, while bringing together researchers from NLP, linguistics, writing systems and language-resource communities. It also highlighted links with the Masakhane NLP community, COMSATS and Lancaster University's UCREL NLP Group.

The name AbjadNLP is used as an inclusive umbrella. The workshop has always recognised that the wider scope includes languages using Arabic and Perso-Arabic alphabets, as well as Ajami writing traditions, and that not every language within this community is technically written using an abjad.

العربية

Arabic

Modern Standard Arabic, dialects, historical language varieties and Arabic NLP.

فارسی · اردو

Perso-Arabic

Persian, Urdu, Pashto, Sorani Kurdish, Sindhi, Uyghur and related writing traditions.

عجمي

Ajami

African languages written using Arabic-derived scripts, including Hausa, Fulfulde, Wolofal, Swahili, Kanuri, Mandingo and Tamazight.

Research scope

Topics represented by the first edition

The original call combined core NLP, writing-system technology, resources and culturally grounded language technology.

Core NLP

Morphology, tokenisation, POS tagging, named entities, parsing, semantic role labelling, sentiment and language modelling.

Applications

Machine translation, speech recognition and synthesis, OCR, pedagogy, assistive technologies and social media analysis.

Language Resources

Dictionaries, annotated datasets, corpora, BLARK descriptions and open-access resources.

Writing Systems

Orthography descriptions, font technology, glyph rendering, Unicode, text input and spell-checking.

Transliteration & Processing

Text processing across Arabic-derived scripts, transliteration and morphology-aware approaches.

Culture & Sociolinguistics

Cultural and sociolinguistic considerations for inclusive NLP applications and language preservation.

Published record

Accepted papers

AbjadNLP 2025 Proceedings

The workshop proceedings are permanently available through the ACL Anthology.

Open Proceedings ↗
01

Developing an Informal-Formal Persian Corpus: Highlighting the Differences between Two Writing Styles

Vahide Tajalli, Mehrnoush Shamsfard and Fateme Kalantari

02

DadmaTools V2: an Adapter-Based Natural Language Processing Toolkit for the Persian Language

Sadegh Jafari, Farhan Farsi, Navid Ebrahimi, Mohamad Bagher Sajadi and Sauleh Eetemadi

03

Towards Unified Processing of Perso-Arabic Scripts for ASR

Srihari Bandarupalli, Bhavana Akkiraju, Sri Charan Devarakonda, Harinie Sivaramasethu, Vamshiraghusimha Narasinga and Anil Vuppala

04

Evaluating Large Language Models on Health-Related Claims Across Arabic Dialects

Abdulsalam Obaid Alharbi, Abdullah Alsuhaibani, Abdulrahman Abdullah Alalawi, Usman Naseem, Shoaib Jameel, Salil Kanhere and Imran Razzak

05

Can LLMs Verify Arabic Claims? Evaluating the Arabic Fact-Checking Abilities of Multilingual LLMs

Ayushman Gupta, Aryan Singhal, Thomas Law, Veekshith Rao, Evan Duan and Ryan Luo Li

06

Can LLMs Translate Cultural Nuance in Dialects? A Case Study on Lebanese Arabic

Silvana Yakhni and Ali Chehab

07

Boosting Sentiment Analysis in Persian through a GAN-Based Synthetic Data Augmentation Method

Masoumeh Mohammadi, Mohammad Ruhul Amin and Shadi Tavakoli

08

In-Depth Analysis of Arabic-Origin Words in the Turkish Morpholex

Mounes Zaval, Abdullah İhsanoğlu, Asım Ersoy and Olcay Taner Yıldız

09

A Derivational ChainBank for Modern Standard Arabic

Reham Marzouk, Sondos Krouna and Nizar Habash

10

Evaluation of Large Language Models on Arabic Punctuation Prediction

Asma Ali Al Wazrah, Afrah Altamimi, Hawra Aljasim, Waad Alshammari, Rawan Al-Matham, Omar Elnashar, Mohamed Amin and Abdulrahman AlOsaimy

11

Evaluating RAG Pipelines for Arabic Lexical Information Retrieval: A Comparative Study of Embedding and Generation Models

Raghad Al-Rasheed, Abdullah Al Muaddi, Hawra Aljasim, Rawan Al-Matham, Muneera Alhoshan, Asma Al Wazrah and Abdulrahman AlOsaimy

12

Automated Generation of Arabic Verb Conjugations with Multilingual Urdu Translation: An NLP Approach

Haq Nawaz, Manal Elobaid, Ali Al-Laith and Saif Ullah

13

Psychological Health Chatbot, Detecting and Assisting Patients in their Path to Recovery

Sadegh Jafari, Mohammad Erfan Zare, Amireza Vishte, Mirzae Melike, Zahra Amiri, Sima Mohammadparast and Sauleh Eetemadi

14

MultiProp Framework: Ensemble Models for Enhanced Cross-Lingual Propaganda Detection in Social Media and News using Data Augmentation, Text Segmentation, and Meta-Learning

Farizeh Aldabbas, Shaina Ashraf, Rafet Sifa and Lucie Flek

15

The Best of Both Worlds: Exploring Wolofal in the Context of NLP

Ngoc Tan Le, Ali Mijiyawa, Abdoulahat Leye and Fatiha Sadat

People behind the first edition

Organising committee

The inaugural workshop was organised by an international team spanning NLP, linguistics, writing systems and low-resource language research.

Advisory committee
Programme Committee
  • Abdoulaye Diallo · Fula & Wolofal · Independent Researcher
  • Ahmed Abdelali · Arabic/Multilingual NLP · Humain, Saudi Arabia
  • Ahmed AbuRa’ed · Arabic · UBC, Canada
  • Alp Oktem · Tigrinya and Kanuri · Translators without Borders
  • Antonio Moreno Sandoval · Low-Resourced Languages · UAM, Spain
  • Azizud Din · Pashto · University Malaysia Sarawak, Malaysia
  • Behnam Sabeti · Persian · Miras Technologies International, Iran
  • Chenggang Mi · Uyghur · Xinjiang Technical Institute, China
  • Clement Oyeleke · Yoruba · University of Ibadan, Nigeria
  • Daniel Whitenack · Kimbundu, Fulfulde, Pular · SIL International, USA
  • Derguene Mbaye · Wolofal · Baamtu, Senegal
  • Djamel Mostefa · Pashto · ELDA, France
  • Doaa Samy · Arabic · Cairo University, Egypt & LLI-UAM, Spain
  • Elias W BA · Fula and Wolofal · Baamtu, Senegal
  • Eric Atwell · Arabic/Multilingual NLP · Leeds University, UK
  • Frederick Apina · Swahili · Parrot.AI, Tanzania
  • George Giannakopoulos · Multilingual NLP · SKEL Lab – NCSR Demokritos, Greece
  • Haithem Afli · Arabic/Multilingual NLP · Dublin City University, Ireland
  • Hazem Hajj · Arabic/Multilingual NLP · American University of Beirut, Lebanon
  • Houda Anoun · Arabic NLP · Hassan II University of Casablanca, Morocco
  • Nassera Habbat · Arabic NLP · Hassan II University of Casablanca, Morocco
  • Houda Bouamor · Arabic/Multilingual NLP · CMU, Qatar
  • Ignatius Ezeani · Igbo, African Languages NLP · Lancaster University, UK
  • Imed Zitouni · Arabic/Multilingual NLP · Microsoft Research, USA
  • Karim Bouzoubaa · Arabic/Multilingual NLP · Mohamed V University, Morocco
  • Mariam Masoud · Kurdish · National University of Ireland Galway, Ireland
  • Lei Wang · Uyghur · Xinjiang Technical Institute, China
  • Muhammad Sharjeel · Urdu · COMSATS University Islamabad, Pakistan
  • Omid Momenzadeh · Persian · Miras Technologies International, Iran
  • Preni Golazizian · Persian · Miras Technologies International, Iran
  • Rao Muhammad Adeel Nawab · Urdu · COMSATS University Islamabad, Pakistan
  • Reza Fahmi · Persian · Miras Technologies International, Iran
  • Samuel Olanrewaju · Yoruba, Yagba and Basa · University of Ibadan, Nigeria
  • Scott Piao · Multilingual and Low-Resourced Languages · Lancaster University, UK
  • Seyed Arad Ashrafi Asli · Persian · Miras Technologies International, Iran
  • Shervin Malmasi · Sorani Kurdish · Macquarie University, Australia
  • Sina Ahmadi · Kurdish · University of Zurich, Switzerland
  • Sokhar Samb · Wolofal · ML & NLP, Senegal
  • Tonghai Jiang · Uyghur · Xinjiang Technical Institute, China
  • Waziri Shebogholo · Swahili · Parrot.AI, Tanzania
  • Wole Akin · IsiXhosa, Yorùbá, Hausa and Igbo · University of Johannesburg, South Africa
  • Xi Zhou · Uyghur · Xinjiang Technical Institute, China
  • Yating Yang · Uyghur · Xinjiang Technical Institute, China
  • Zahra Majdabadi · Persian · Miras Technologies International, Iran
Workshop series

From the first edition to a continuing community

AbjadNLP 2025 established the workshop series and its broad community focus. Later editions continue the same mission while expanding the programme, shared tasks and participation across Arabic-script language communities.

2025 · Abu Dhabi

1st AbjadNLP

Inaugural edition, co-located with COLING 2025.

2026 · Rabat

2nd AbjadNLP

Second edition at EACL 2026.

2027 · Athens

3rd AbjadNLP

Current edition at EACL 2027.