Advancing NLP and responsible AI for the Iranian language family.
We are a community of linguists, NLP researchers, engineers, and Iranologists working together to build computational tools and resources for one of the world's most linguistically diverse language families.
🗣️ Persian (Farsi) · Kurdish · Pashto · Dari · Tajik · Balochi · Gilaki · Mazandarani · Luri · Ossetic · Shughni · and more
- Resources & Datasets — Curating and building NLP datasets for under-resourced Iranian languages
- Research — Publishing papers on language models, machine translation, speech processing, and content moderation
- Community — Connecting researchers across institutions to close the resource gap for Iranian languages
- Workshops — Organizing forums at top NLP venues for knowledge exchange
| 🌐 Website | silkroadnlp.org |
| 📚 Resources | awesome-SilkRoadNLP — curated list of NLP resources for Iranian languages |
| 📄 Proceedings | EACL 2026 SilkRoadNLP Proceedings |
| 🤝 Contribute | How to contribute — add papers, share projects, contribute data |
- Add a resource — Know a paper, dataset, or tool? Fork the awesome list and submit a PR
- Share your project — Working on Iranian-language NLP? Get it listed or hosted under the org
- Contribute data — Even small word lists or transcriptions help for under-resourced languages like Balochi, Luri, and Shughni
- Present your work — Submit to future SilkRoadNLP workshop calls for papers