OSACT6 Image

Welcome to OSACT7


The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks (Hybrid)

Palma, Mallorca (Spain)
11-16 May 2026.
Co-located with LREC 2026

Workshop Description


The Open-Source Arabic Corpora and Processing Tools (OSACT) workshop series provides a forum for researchers, practitioners, and students in computational linguistics (CL), natural language processing (NLP), and information retrieval (IR) to share and discuss ongoing work on Arabic language resources and technologies. While Arabic remains comparatively resource-poor in relation to English, recent years have seen the emergence of large, freely available classical and Modern Standard Arabic (MSA) corpora, as well as dialectical corpora and processing tools.

Now in its seventh edition, OSACT7 takes an important step forward by celebrating this milestone with seven shared tasks, each addressing timely challenges in Arabic NLP and reflecting broader themes relevant to NLP research in general. OSACT7 builds on its long-standing commitment to open-source contributions that advance accessibility, reproducibility, and fairness, and this year it places inclusivity at the heart of its mission. A key focus is to recognize and support minority dialects and underrepresented varieties of Arabic, ensuring that diverse linguistic voices and resources are not only acknowledged but actively valued within the community.

The workshop will cover general topics in CL, NLP, and IR, with special emphasis on Large Language Models (LLMs) and Generative AI, including pre-trained Arabic language models, corpus design and evaluation, and annotated corpora for tasks such as named entity recognition, machine translation, sentiment analysis, and text classification. Additional areas of focus include crowdsourcing for data annotation, tools for language education, tokenisation, normalisation, morphological analysis, part-of-speech tagging, dialect identification and translation, fake news detection, and web and social media analytics. Methodologies for resource creation and annotation, knowledge extraction, ontologies, terminology, knowledge representation, and integration with the Semantic Web (e.g. Linked Data, Knowledge Graphs) will also be explored.

Shared Tasks

OSACT7 will host five shared tasks, each organised by a dedicated team:

  1. QIAS 2026: Questions & Answers in Islamic Studies Assessment
  2. AdabEval 2026: Arabic Politeness Detection
  3. AraSentEval 2026: A Shared Task on Sentiment Analysis and Swapping in Arabic
  4. AraHAHA 2026: Arabic Humour Generation
  5. KSAA 2026: Arabic Speech Dictation with Automatic Diacritisation
    • Organizers: Waad Alshammari, Asma Al Wazrah, Rawan Almatham, Afrah Altamimi, Raghad Al-Rasheed, Sawsan Alqahtani, Hanan Aldarmaki, Rufael Marew, Abdulrahman Alshehri, Mohamed Assar, Abdullah Alharbi, Abdulrahman AlOsaimy (King Salman Academy, Princess Nourah University and MBZUAI)
    • For more information, please visit the shared task website: https://arai.ksaa.gov.sa/sharedTask2026/
    • System paper submission link: https://softconf.com/lrec2026/OSACT7/ Choose KSAA 2026 Track

Workshop Topics

Language Resources:

  • Pre-trained Arabic language models.
  • Surveys and evaluations of existing Arabic corpora and their associated processing tools.
  • Development and release of new annotated corpora for NLP and IR tasks such as named entity recognition, machine translation, sentiment analysis, text classification, and language learning.
  • Assessing the effectiveness of crowdsourcing platforms for Arabic data annotation.
  • Arabic text and speech processing toolkits.

Tools and Technologies:

  • Language education, including first (L1) and second (L2) language learning applications.
  • Pre-training & fine-tuning approaches for Arabic.
  • Tokenisation, normalisation, segmentation, morphology, and POS tagging.
  • Sentiment analysis, dialect ID, \& classification.
  • Web and social media analytics.
  • Arabic LRs for text, speech, sign, gesture, image, & multimodal data.
  • Best practices for LR interoperability.
  • Construction and annotation of LRs.
  • Knowledge extraction, acquisition, and representation.
  • Ontologies, terminology, and frameworks.
  • LRs and the Semantic Web (Linked Data, Knowledge Graphs).
  • Data contamination, synthetic data, and quality issues.

Paper Types and Formats


OSACT6 invites high-quality submissions written in English. Submissions of two forms of papers will be considered:

  1. Regular long papers – up to eight (8) pages maximum*, presenting substantial, original, completed, and unpublished work.
  2. Short papers – up to four (4) pages*, describing a small focused contribution, negative results, system demonstrations, etc.

* Excluding any number of additional pages for references, ethical consideration, conflict-of-interest, as well as data, and code availability statements.

Upon acceptance, final versions of long papers will be given one additional page – up to nine (9) pages of content plus unlimited pages for acknowledgments and references – so that reviewers’ comments can be taken into account. Final versions of short papers may have up to five (5) pages, plus unlimited pages for acknowledgments and references. For both long and short papers, all figures and tables that are part of the main text must fit within these page limits.

Furthermore, appendices or supplementary material will also be allowed ONLY in the final, camera-ready version, but not during submission, as papers should be reviewed without the need to refer to any supplementary materials.

Linguistic examples, if any, should be presented in the original language but also glossed into English to allow accessibility for a broader audience.

Note that paper types are decisions made orthogonal to the eventual, final form of presentation (i.e., oral versus poster).

Important Dates

Important Dates

  • February 18, 2026: Paper submission deadline
  • March 12, 2026 Notification of acceptance
  • March 30, 2026: Camera-ready deadline
  • May 11, 2026: Workshop Date

Submission guidelines

We follow the LREC 2026 standards for submission format and guidelines.

  • Long papers: up to 8 pages (excluding references). Substantial, original, and completed work.
  • Short papers: up to 4 pages (excluding references). Suitable for focused contributions, negative results, datasets, or system descriptions.
  • Shared task papers: up to 4 pages (excluding references). Suitable for focused contributions, negative results, datasets, or system descriptions.

Submission Link: https://softconf.com/lrec2026/OSACT7/

Accepted Papers

Keynote Speaker

Committees

Organizing Committee

  • Hend Al-Khalifa, Professor, King Saud University, Riyadh, Saudi Arabia, hendk@ksu.edu.sa
  • Mo El-Haj, Reader, VinUniversity, Vietnam, Lancaster University, UK, elhaj.m@vinuni.edu.vn
  • Saad Ezzini, Assistant Professor, King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia, saad.ezzini@kfupm.edu.sa

Programme Committee

  • Mohammed Alliheedi, Al-Baha University, Saudi Arabia
  • Mamoun Abu Helou, Al-Istiqlal University, Palestine
  • Mohammad A. M. Abushariah, The University of Jordan, Jordan
  • Majdi Sawalha, The University of Jordan, Jordan
  • Maria Bounnit, FLAM, Cadi Ayyad University, Morocco
  • Hani M. Iwidat, Al-Istiqlal University, Palestine
  • Noorhan Abbas, University of Leeds, United Kingdom
  • Sultan Alrowili, IBM Research, Saudi Arabia
  • Abdulaziz Alhamadani, Florida Polytechnic University, United States
  • Amal Haddad Haddad, University of Granada, Spain
  • Dima Taji, Charles University, Czech Republic
  • Hamada Nayel, Prince Sattam Bin Abdulaziz University, Saudi Arabia
  • Salmane Chafik, Mohammed VI Polytechnic University, Morocco
  • Abdessalam Bouchekif, Hamad Bin Khalifa University (HBKU), Qatar
  • Sharefah Al-Ghamdi, King Saud University, Saudi Arabia
  • Akram Mohammed Ahmed Al-Rumaim, Independent Researcher, Netherlands
  • Ashraf Elnagar, University of Sharjah, United Arab Emirates
  • Ameera Almasoud, King Saud University, Saudi Arabia
  • Imed Zitouni, Meta, United States
  • Mohammad Abuoudeh, Al-Hussein Bin Talal University, Jordan
  • Wajdi Zaghouani, Northwestern University in Qatar, Qatar
  • Rana Malhas, Qatar University, Qatar
  • Ehsan Lotfi, University of Antwerp, Belgium
  • Abdelkader El Mahdaouy, Mohammed VI Polytechnic University, Morocco
  • Khalid Choukri, ELRA/ELDA, France
  • Khalid Al-Khatib, University of Groningen, Netherlands
  • Amany Fashwan, Phonetics and Linguistics Department, Faculty of Arts, Alexandria University, Egypt
  • Salima Harrat, École Normale Supérieure de Bouzaréah (ENSB), Algiers, Algeria
  • Manal Albahlal, King Saud University, Saudi Arabia
  • Wafa Aissa, UCLouvain, Belgium
  • Bassam Haddad, University of Petra, Jordan
  • Noof Alfear, King Saud University, Saudi Arabia
  • Amr Keleg, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), United Arab Emirates
  • Sara Nabhani, University of Groningen, Netherlands
  • Ali Al-Laith, University of Copenhagen, Denmark
  • Fethi Bougares, Elyadata, LIA – Université d'Avignon, France
  • Amal Htait, Aston University, United Kingdom
  • Oussama Ben Khiroun, University of Manouba, Tunisia
  • Nadia Ghezaiel, University of Ha'il, Saudi Arabia
  • Assal A. M. Alqudah, Al-Balqa Applied University, Jordan
  • Omar Trigui, University of Sousse, Tunisia
  • Paul Rayson, Lancaster University, United Kingdom
  • Hamza Alami, L3IA Laboratory, USMBA, Morocco
  • Abdulhamid Abubakar, Center for Cyberspace Studies, NSU Keffi, Nigeria
  • Kamel Gaanoun, INSEA, Morocco

Workshop Program