Tejinder Singh Saini

Shahmukhi to Gurmukhi Transliteration System: Addressing Script Challenges with Statistical and Rule Based Approach Tejinder Singh Saini

Punjabi language, spoken by tens of millions of peoples worldwide, is one among those unique languages of the world which are written in different scripts. It is written in Indian East Punjab in Gurmukhi script, in Pakistan West Punjab, in Shahmukhi script. Whilst in speech, Punjabi in the both Eastern and the Western Punjab is mutually comprehensible, in the written form it is not so. This has created a script barrier between the Punjabi literature written in India and in Pakistan. A computer program capable of automatic transliteration between Shahmukhi and Gurmukhi scripts is a great boon for overcoming the script barrier in Punjabi language. This book addresses the challenges posed by Shahmukhi script and proposes a complete Shahmukhi-to-Gurmukhi transliteration system which is capable of processing the real life or natural Shahmukhi text. The book also highlights the difficulties encountered during transliteration like filling the missing diacritics, missing short vowels, multiple mappings, word boundary issues and word sense disambiguation which were no trivial and presents their promising solutions during different stages of development of the transliteration system.