.png)
SilkRoadNLP 2026
Call for Papers
1st Workshop on NLP and Large Language Models for the Iranian Language Family
March 28 or 29, 2026. Rabat, Morocco.
(Workshop Date to be confirmed)
co-located with
The 19th Conference on the European Chapter of the Association for Computational Linguistics (EACL 2026)
Questions?
Feel free to contact us with any questions.
Overview
The inaugural SilkRoadNLP workshop provides a platform for advancing Natural Language Processing (NLP) and Large Language Models (LLMs) for the Iranian linguistic family—a diverse group of languages spoken across Iran, Afghanistan, Central and South Asia, and the Caucasus. We welcome work that bridges computational methods with linguistic, social, and cultural perspectives to ensure that the technologies shaping the future of language reflect this region’s diversity and depth.
Recent advances in LLMs have transformed the field of NLP, yet the languages of the Iranian linguistic group remain underrepresented. While Persian has received some attention, many languages and dialects of the Iranian language family—such as Kurdish, Balochi, Gilaki, Mazandarani, Luri, Pashto, Ossetian, and others—remain low-resource, with limited digital presence, benchmarks, and system support. Many of these minority languages are endangered or at risk of further marginalization. Even within Persian, regional standards (Iranian, Afghan/Dari, and Tajiki) differ substantially in orthography, phonology, and lexicon, creating additional complexity for multilingual NLP and LLM adaptation.
SilkRoadNLP will be the first ACL-affiliated forum dedicated to the computational study of the Iranian language family in the LLM era. The workshop aims to:
-
Highlight advances in NLP analysis, datasets, benchmarks, and modeling
-
Explore responsible LLM extensions
-
Address cultural and socio-pragmatic challenges
-
Foster cross-disciplinary collaboration
-
Create a centralized resource hub
We welcome research on all languages of the Iranian linguistic family, including those spoken across Central Asia, the Caucasus, Afghanistan, Pakistan, and diaspora communities, reflecting the broad reach of the linguistic group.
** See list of all Iranian languages accepted at SilkRoadNLP 2026.
Topics of Interest
We invite submissions on any aspect of NLP, computational linguistics, or LLM research relevant to the Iranian linguistic family, including but not limited to:
-
Computational linguistic analysis of Iranian languages: morphology, syntax, semantics, typology.
-
Resource creation (corpora, benchmarks, lexicons), documentation and annotation for modern and endangered languages.
-
Speech and multimodal processing (ASR, TTS, multimodal learning).
-
OCR, digitization tools, and script technologies for diverse scripts.
-
LLM adaptation, fine-tuning, and evaluation in any domain.
-
NLP for historical and extinct Iranian languages (e.g., Pahlavi, Avestan, Sogdian) for digital humanities and cultural heritage.
-
NLP for dialects, heritage languages, and minority varieties.
-
Machine translation, transliteration, and cross-script processing.
-
Evaluation frameworks and shared tasks.
-
Educational applications and language learning tools.
-
Ethical, culturally aware, and community-centered NLP approaches.
-
Downstream and applied NLP tasks (e.g., sentiment analysis, misinformation detection, information retrieval, social media analytics, health and legal NLP, etc.)Linguistic analysis (morphology, syntax, semantics, typology)
Submission Format
We invite the following categories of submissions:
-
Long papers: Up to 8 pages (excluding references).
Long paper submissions must describe substantial, original, completed and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. Long papers may consist of up to 8 pages of content, plus unlimited pages for references and appendices. Upon acceptance, long papers will be given one additional page of content (i.e. up to 9 pages) in the proceedings so that reviewers’ comments can be taken into account. -
Short papers / demo papers: Up to 4 pages (excluding references).
Short paper submissions must describe original and unpublished work. Please note that a short paper is not a shortened long paper. Instead, short papers should have a point that can be made in a few pages. Short papers may consist of up to 4 pages of content, plus unlimited references and appendices. Upon acceptance, short papers will be given one additional page of content (i.e. up to 5 pages) in the proceedings so that reviewers’ comments can be taken into account.
All papers submitted to the workshop must be fully anonymized for double-blind review.
All submissions must follow the official ACL 2026 style templates (LaTeX or Word).
Submission & Review
-
Submissions will be handled through OpenReview.
-
Reviews will be double-blind; please remove author names and affiliations.
-
ARR or OpenReview commitments will not be accepted for this edition.
-
Accepted papers will be published in the ACL Anthology as part of the EACL 2026 workshop proceedings.
Hybrid Participation
The workshop will be held in a collaborative hybrid format, combining in-person sessions in Rabat with online participation to ensure wide accessibility. The workshop will feature live-streamed talks, virtual poster sessions, and interactive Q&A opportunities for remote attendees. Final details on the hybrid setup will be shared closer to the event in coordination with EACL 2026.
Important Dates
-
Call for Papers: 20 October 2025
-
Direct Submission Deadline: 8 January 2026
-
Notification of Acceptance: 26 January 2026
-
Camera-ready Papers Due: 3 February 2026
-
Poster Boards Due: 5 February 2026
-
Workshop Dates: 28 or 29 March 2026 (TBD)
All deadlines are 11:59 PM UTC-12 (“anywhere on Earth”).
Diversity & Inclusion
SilkRoadNLP is committed to inclusive participation. We strongly encourage submissions from early-career researchers, independent scholars, and institutions in low-resource regions. The workshop will support hybrid participation (onsite + virtual) to maximize accessibility.