Optimizing Transliteration for Hindi/Marathi to English Using only Two Weights

摘要

Machine transliteration has received significant research attention in last two decades. It is observed that Hindi to English and Marathi to English named entity machine transliteration is comparably less studied. Currently, research work in this domain is carried out by using grapheme based statistical approaches. But, to achieve better accuracy for the transliteration, an adequate bilingual text corpus is a mandatory requirement for statistical approaches. This paper focuses on Hindi to English and Marathi to English direct machine transliteration of Indian-origin named entities such as proper names, place names and organization names. Proposed phonetic based statistical approach uses phoneme and named entity length as features for supervised learning and transliterates them in English using full consonant based phonetic scheme without support of corpus. This system takes Indian origin named entities as an input in Hindi and Marathi using Devanagari script and transliterates it into English by using only two weights.