Abstract:
Machine translation (MT) of English text to its Urdu equivalent is a difficult challenge, and one that has not been tackled with much success to date. In this dissertation, a direct approach is being presented using an expert system, which successfully generates Romanized Urdu from English text. The expert system works with a knowledge base that contains grammatical patterns of English and Urdu. The Romanized Urdu generated by this system is understandable by non-English speaking individuals who are familiar with the English alphabets.
Determining a workable methodology for this research was quite challenging, as very little precursor research exists on the problem of English to Urdu machine translation. However after some analysis, it was decided to study the approach used for English to Japanese machine translation. This approach was potentially useful as both Japanese and Urdu are SOV (subject, object and verb) languages, whereby the verb in a given sentence appears at the end.
