Urdu is a rich language with a multilingual and multi cultural heritage. Its roots in Arabic, English, Persian, Sanskrit and other languages give Urdu a diverse body of sounds and underlying linguistic structure. Similarly, multi cultural background introduces a varied tradition of calligraphy, prose poetry, and other forms of art in Urdu. This rich heritage makes Urdu far more computationally interesting and challenging than any other language. This is also true for Pakistan’s other regional languages including Sindhi, Pushto, Balochi and Brohvi. These challenges pose a vast unexplored training field for research students in computer science.
Center for Research in Urdu Language Processing (CRULP) is conducting research and development in linguistic and computational aspects of Urdu and other languages of Pakistan. Formation of CRULP was announced at the “First National Urdu Software Development Workshop” held in March 2001 at FAST-NU, Lahore and was established in July 2001. The center was established to conduct research and development in three areas including Speech Processing, Computational Linguistics and Script Processing. In addition, this center also arranges and participates in seminars, workshops and conferences dedicated to promote Urdu Language processing. This work will be instrumental in development of Urdu computing in Pakistan. The research potential in aspects of the Urdu and regional languages in Pakistan is enormous, as very little work has so far been done in this field.