.png)
About SilkRoadNLP
SilkRoadNLP is an ACL-affiliated workshop and emerging community 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 due to underrepresentation in data, benchmarks, and deployed systems.
We have launched the SilkRoadNLP Community Hub (GitHub) to share papers, datasets, tools, and ongoing developments, and to support continued collaboration beyond the workshop.
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 to this moment by fostering a collaborative, interdisciplinary space for research and resource development that supports both technological advancement and linguistic and cultural continuity.
Participation and Access
SilkRoadNLP 2026 was held in Rabat, Morocco as part of EACL 2026.
Given the geographic and political realities affecting many contributors, participation included both in-person and remote engagement where possible. Workshop materials, papers, and resources are available through the SilkRoadNLP Community Hub to ensure continued access and reuse.
We remain committed to broad and inclusive participation in future iterations of SilkRoadNLP.
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 through shared resources, future sorkwhops, and sustained collaboration networks.
A Growing Global Movement
SilkRoadNLP aligns with broader community efforts such as AfricaNLP, AmericasNLP, and SIGTYP, which aim to elevate underrepresented languages and regionally grounded NLP. By focusing on the Iranian linguistic family, SilkRoadNLP contributes to this global movement by supporting community-led, ethically grounded AI and the development of shared resources in the LLM era.