English to Sanskrit machine translation system: a rule-based approach

Abstract

The development of machine translation (MT) system for ancient language such as Sanskrit is a much more fascinating and challenging task. Due to lack of linguistic community, there are no wide works accomplished in Sanskrit translation while it is national language by virtue of its importance in India's cultural heritage. This paper describes a rule-based approach of machine translation which translates an English sentence (source language sentence) into equivalent Sanskrit sentence (target language sentence). Due to morphological richness of Sanskrit language, this system makes limited use of syntax and uses only morphological markings to identify subject, object, verb, preposition, adjective and adverb, as well as conjunctive sentences. It uses limited parsing for part of speech (POS) tagging, identification of clause, its subject, object, verb, etc and gender-number-person (GNP) of noun and object. This system gives translation result in GUI form and handles English sentences of different classes. The performance evaluations of our EST system with different methods of MT evaluations are shown using table and column chart.