Update README.md

README.md

@@ -1,10 +1,187 @@
 ---
-title: README
-emoji: 💻
-colorFrom: pink
-colorTo: purple
+title: BashkirNLP - Turkic & Low-Resource Languages
+emoji: 🏔️
+colorFrom: green
+colorTo: blue
 sdk: gradio
-pinned: false
+pinned: true
+license: mit
+short_description: Bashkir & Turkic NLP for low-resource languages.
+sdk_version: 6.6.0
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+# BashkirNLP – Turkic & Low‑Resource Languages Research Hub
+
+![Status](https://img.shields.io/badge/Status-Active-brightgreen)
+![Focus](https://img.shields.io/badge/Focus-Bashkir_Language-blue)
+![Focus](https://img.shields.io/badge/Focus-Turkic_NLP-orange)
+![Focus](https://img.shields.io/badge/Focus-Low_Resource_Languages-red)
+
+**BashkirNLP** is a collaborative research initiative dedicated to advancing natural language processing for **Bashkir**, **Turkic languages**, and **low‑resource languages** in the Ural-Volga region and beyond. We develop state‑of‑the‑art language models, machine translation systems, linguistic resources, and educational tools to empower under‑represented languages in the digital age.
+
+---
+
+## 🎯 Our Mission
+
+- Build **open‑source language models** for Bashkir and other Turkic varieties (Tatar, Kazakh, Chuvash, etc.).
+- Create **high‑quality linguistic resources** (corpora, lexicons, evaluation benchmarks).
+- Advance **machine translation** between Bashkir, Russian, English, and major Turkic languages.
+- Develop **educational materials** and interactive demos to lower the entry barrier for low‑resource NLP.
+- Foster a community of researchers, developers, and native speakers working together on language technology.
+
+---
+
+## 🚀 Interactive Demos
+
+Explore our live Hugging Face Spaces and try out our models directly in your browser:
+
+### **🔤 Language Models**
+- **[BashkirGPT Playground]()** – Generate and analyze Bashkir text with our latest causal LM.
+- **[TurkicBERT Explorer]()** – Masked language modelling for Bashkir, Tatar, and other Turkic languages.
+- **[Multilingual Embeddings]()** – Compare word/sentence vectors across Turkic languages.
+
+### **🌐 Machine Translation**
+- **[Bashkir ↔ Russian Translator]()** – Neural translation between Bashkir and Russian.
+- **[Bashkir ↔ Tatar Translator]()** – Translation demo for closely related Turkic languages.
+- **[Bashkir ↔ English Translator]()** – Experimental translation for low-resource pairs.
+
+### **📚 Linguistic Tools**
+- **[Bashkir Morphological Analyzer]()** – Interactive segmentation and POS tagging (Cyrillic & Latin scripts).
+- **[Named Entity Recognition for Bashkir]()** – Identify persons, locations, organizations.
+- **[Script Converter]()** – Convert between Cyrillic Bashkir and Latin-based orthographies.
+
+### **📊 Data & Benchmarks**
+- **[Bashkir Corpus Explorer]()** – Browse and query our curated text collections.
+- **[Turkic NLP Leaderboard]()** – Compare model performance on Bashkir, Tatar, and other Turkic tasks.
+- **[Annotation Tools]()** – Help us improve datasets with your feedback.
+
+*Click on any demo to start experimenting – no installation required!*
+
+---
+
+## 🧠 Research Focus Areas
+
+### **🏞️ Bashkir Language Technologies**
+- Creation of the first large‑scale pretrained models for Bashkir (Cyrillic script, with Latin adaptation).
+- Morphological disambiguation and syntactic parsing for Bashkir (agglutinative morphology).
+- Speech recognition and synthesis for Bashkir (coming soon).
+
+### **📜 Turkic NLP**
+- Cross‑lingual transfer learning among Bashkir, Tatar, Kazakh, and other Kipchak languages.
+- Unified tokenization and subword models for the Turkic language family.
+- Machine translation between Turkic languages and major world languages.
+
+### **📉 Low‑Resource NLP**
+- Data augmentation and semi‑supervised learning techniques.
+- Leveraging multilingual models (e.g., mT5, XLM‑R, Turkmenglish) for under‑represented languages.
+- Few‑shot and zero‑shot learning for tasks like NER and sentiment analysis.
+
+### **🤖 Language Models**
+- Pretraining from scratch and continued pretraining on Bashkir/Turkic corpora.
+- Efficient architectures (ALBERT, DistilBERT) for low‑resource settings.
+- Evaluation and bias analysis of Turkic language models.
+
+### **📖 Linguistic Resources**
+- **Corpora**: News, literature, web‑crawled texts, social media (e.g., VK, Telegram).
+- **Lexicons**: Morphological dictionaries, wordnets, sentiment lexicons.
+- **Benchmarks**: Named entity recognition, part‑of‑speech tagging, machine translation test sets.
+
+---
+
+## 📦 Models & Datasets
+
+We release all our models and datasets on Hugging Face Hub under open licenses.
+
+| Model / Dataset | Description | Link |
+|-----------------|-------------|------|
+| **BashkirBERT** | BERT‑base model pretrained on Bashkir Cyrillic texts | [🤗 Hub]() |
+| **Turkic‑mT5** | Multilingual T5 fine‑tuned on Bashkir, Tatar, and Kazakh | [🤗 Hub]() |
+| **Bashkir‑MT‑BaRu** | Transformer��based translation model (Bashkir ↔ Russian) | [🤗 Hub]() |
+| **Bashkir‑NER** | Named entity recognition model for Bashkir | [🤗 Hub]() |
+| **BashkirCorpus v1.0** | 100M token corpus from news, books, and websites | [🤗 Dataset]() |
+| **Turkic‑Parallel‑Bench** | Parallel sentences for Bashkir, Tatar, and Turkish | [🤗 Dataset]() |
+
+*More models and datasets are added regularly. Follow our [organization page](https://huggingface.co/BashkirNLP) for updates.*
+
+---
+
+## 📚 Educational Resources
+
+We believe in **open education** and **reproducible research**. All our tutorials and teaching materials are freely available.
+
+- **[Interactive Notebooks]()** – Hands‑on tutorials for building low‑resource NLP systems (in Python, using Hugging Face libraries).
+- **[Video Lectures]()** – Recorded talks on Bashkir/Turkic NLP, data collection, and model training.
+- **[Course Materials]()** – Slides, readings, and assignments from our university courses.
+- **[Blog Posts]()** – Deep dives into challenges and solutions for Bashkir and Turkic languages.
+
+---
+
+## 📝 Selected Publications
+
+1. *"BashkirBERT: A Pretrained Language Model for Bashkir"* – LREC 2025 (planned)  
+2. *"Machine Translation for Low-Resource Turkic Languages: Bashkir–Russian Case Study"* – WMT 2024  
+3. *"Building a Named Entity Recognition Dataset for Bashkir"* – TurkicLang 2024  
+4. *"Multilingual Representations for Kipchak Languages: A Comparative Study"* – EMNLP 2023  
+5. *"Bashkir Corpus: Collection, Annotation, and Baseline Experiments"* – Dialogue 2023  
+
+*Full list with links to PDFs available on our [Publications Page]().*
+
+---
+
+## 🤝 Get Involved
+
+We welcome contributions from the community – whether you are a researcher, developer, student, or native speaker.
+
+### **For Researchers**
+- Use our models and datasets in your work (and cite us!).
+- Collaborate on joint papers and grant proposals.
+- Contribute new benchmarks or evaluation tasks.
+
+### **For Developers**
+- Integrate our models into your applications.
+- Report bugs or suggest improvements via GitHub Issues.
+- Submit pull requests to our open‑source repositories.
+
+### **For Native Speakers & Linguists**
+- Help us validate translations and annotations.
+- Share texts or corpora (with permission) to enrich our data.
+- Provide feedback on model outputs to reduce errors.
+
+### **For Students**
+- Use our demos and tutorials for learning.
+- Participate in our mentorship program or summer schools.
+- Start your own research project with our support.
+
+---
+
+## 🌐 Connect With Us
+
+- **🤗 Hugging Face**: [BashkirNLP](https://huggingface.co/BashkirNLP) – Models, datasets, and spaces.
+- **💻 GitHub**: [BashkirNLP](https://github.com/BashkirNLP) – Source code, development, and issue tracking.
+- **📧 Email**: [contact@bashkirnlp.org](mailto:contact@bashkirnlp.org) – General inquiries and collaboration.
+- **📝 Blog**: [Medium/BashkirNLP](https://medium.com/bashkirnlp) – In‑depth articles.
+
+---
+
+## 🔄 Ecosystem Integration
+
+Our work is integrated with the broader Hugging Face ecosystem:
+
+- **Models** on the Hub with easy‑to‑use pipelines.
+- **Datasets** with streaming and evaluation scripts.
+- **Spaces** for interactive demos and educational tools.
+- **Gradio** apps for user‑friendly interfaces.
+
+---
+
+**Empowering Bashkir and Turkic languages through open science and community collaboration.**
+
+<div align="center">
+
+[![Hugging Face](https://img.shields.io/badge/🤗-BashkirNLP-yellow)](https://huggingface.co/BashkirNLP)
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-black)](https://github.com/BashkirNLP)
+[![Twitter](https://img.shields.io/badge/Twitter-@BashkirNLP-blue)](https://twitter.com/BashkirNLP)
+
+**© 2026 BashkirNLP** – Open source for low‑resource languages.
+
+</div>