.png)
About SilkRoadNLP
SilkRoadNLP is the first ACL-affiliated workshop dedicated to advancing Natural Language Processing (NLP) and Large Language Models (LLMs) for the Iranian linguistic family — a diverse network of languages spoken across Iran, Afghanistan, Central and South Asia, the Caucasus, and diaspora communities.
Our mission is to bring together computational linguists, AI researchers, linguists, language specialists, and community experts to foster open collaboration, share resources, and promote culturally informed, inclusive, and ethical approaches to multilingual AI.
As large language models increasingly shape the future of language technology, SilkRoadNLP underscores a simple truth: without intentional inclusion, many languages risk digital marginalization by remaining underrepresented in data, benchmarks, and deployed systems.
We have launched a SilkRoadNLP Community Hub (GitHub) to share accepted papers, datasets, tools, and ongoing updates.
Why Now
Languages of the Iranian linguistic family — including Persian (Farsi), Dari, Tajik, Kurdish (Sorani and Kurmanji), Balochi, Gilaki, Mazandarani, Luri, Pashto, Ossetic, and other related varieties — represent thousands of years of shared history, literature, and oral tradition. Yet many remain low-resource in NLP, lacking open datasets, benchmarks, and digital infrastructure.
The rise of LLMs amplifies both opportunity and risk. While these models promise new tools for cross-lingual communication, education, and access, they can also reinforce data imbalances that marginalize under-documented languages.
SilkRoadNLP responds by providing a collaborative, interdisciplinary venue for computational work that advances research while supporting linguistic and cultural heritage through responsible, community-centered methods.
Our Goals
-
Advance research in NLP and LLMs for low-resource Iranian languages.
-
Develop and share open resources, benchmarks, and evaluation tools.
-
Foster interdisciplinary collaboration among linguists, technologists, and community organizations.
-
Promote responsible and culturally grounded AI that represents, rather than replaces, local voices.
-
Build continuity beyond 2026 through shared resources, potential shared tasks, and sustained collaboration networks.
Participation Format
SilkRoadNLP 2026 takes place in-person in Rabat, Morocco as part of EACL 2026. We are committed to broad participation across regions and will support remote engagement where feasible and consistent with EACL policies.
If remote participation options are available (e.g., streaming, asynchronous access, or online Q&A), we will post details on the website and in the Community Hub. Regardless of attendance mode, we will share workshop outputs and resources through the SilkRoadNLP Community Hub to ensure the work remains accessible and reusable.
A Growing Global Movement
SilkRoadNLP aligns with community efforts such as AfricaNLP, AmericasNLP, and SIGTYP that elevate underrepresented languages and regionally grounded NLP. We extend this spirit to the Iranian language family, emphasizing community-led, ethical AI and shared resources in the LLM era.