Computational linguistics is the scientific study of natural languages from a computational perspective. Computational linguistics was introduced in early attempts in 1946. These attempts include the translation of Russian to English. In fifties and sixties, the US and Great Britain dedicated a number of resources to these kind of applications. However, after the joining of continential Europe, the first system introduced was the SYSTRAN. This production made it clear that the theoretical difficulties of the task could not be underestimated. Then machine oriented approaches appeared with quite efficient results but still no fully automatic high quality systems are available. Today, it is proved that the theoretical linguistic knowledge and machine oriented approaches together can produce better results rather than working independently.


This society of computational linguistics mainly deals with the local languages of Pakistan for their promotion due to the fact that all languages are lying in the category of under-resourced languages, however its scope is not limited to Pakistani languages. Among more than 72 languages in Pakistan, Urdu, Saraiki, Punjabi, Pashto, Sindhi, Balochi are the mojor languages, which are also known as provincial languages except Urdu and Saraiki. Urdu is the national language of Pakistan, while Saraiki is spoken in the South Punjab. Research and development in computational perspective will enable the local community to march with the state of the art standards of information, education, communication, economy, etc.