An expert system driven approach to generating natural language in Romanized Urdu from English documents

Abstract

Machine translation of English text to its Urdu equivalent is a difficult challenge, and one that has not been tackled with much success to date. We present a direct approach, 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, as well as a tense and gender-aware dictionary of Urdu words (with their English equivalents). The Romanized Urdu generated by this system is understandable by non-English speaking individuals who are familiar with the English alphabets. It is also suitable to be used as input in text-to-speech synthesizers for the benefits of individuals that are unable to read.