ENGLISH TO HINDI TRANSLITERATION SYSTEM USING COMBINATION-BASED APPROACH
Baljeet Kaur Dhindsa · International Journal of Advanced Research in Computer Science · 2017
Transliteration plays a very significant role in machine translation, which has many applications such as cross-lingual information retrieval, communication, question-answering etc. The main objective of this research paper is to provide a method for transliteration of named entities from English to Hindi language. The proposed method consists of two modules, both of which apply phoneme-based approach to transliterate named entities. For transliteration, Module-I utilizes CMU Pronouncing dictionary, which is a collection of 133270 words along with their pronunciation. If the word to be transliterated is not found in CMU Pronouncing dictionary, Module-II is used. Module-II is based on 5-gram model, in which a maximum of five letters (two left, two right and one target letter) are used to generate transliterated target letter. The system has been tested on a database of 2408 North-Indian names. Google Input tool for Windows has been used for comparative study of the proposed transliteration system. The word accuracy of the transliteration system has been found to be 70.22% against 58.73% of Google Input tool.