Research community for Urdu NLP.

Urdu is widely known as the national language of Pakistan. Our aim is to promote the Digitization of Urdu Language. In today’s era of Machine Learning and Artificial intelligence, data plays a crucial role but Urdu language has not much availability of data. We started off with simple pre-processing of language and went on to building great Deep Learning models for different NLP tasks. We have been able to achieve great results so far but we are still far from building state of the art solutions for the Urdu Language. To accelerate research and development, we have open sourced this platform.

We believe open-source is more than open source code. It’s a lot about people, collaboration, transparency and trust. Therefore, we decided to be as open as possible with our roadmap and sprint planning. Your ideas for improvement or contributions to the development of Urduhack will be highly encouraged and appreciated.