Automatic English to Kannada Back-Transliteration Using Combination-Based Approach

Abstract

The task of mapping graphemes or phonemes of one language into phoneme approximations of another language is known as machine transliteration. The paper describes transliteration of Romanized Kannada words to Kannada script. Our system utilizes a bilingual corpus of around 3 lakh words, which comprise pairs of Romanized Kannada word with its corresponding word in Kannada script and employs orthographic and phonetic information. Romanized Kannada words are segmented into phonemes by predefined rules. These phonemes are transliterated to Kannada script statistically based on probabilities. The paradigm is assessed with 3000 Romanized Kannada test words and obtained an accuracy of 85.4%.