Transliterating Bangla to English: A Rule-Based Phonetic Approach and A Suggestion System

Transliteration of Bangla to English is a major problem in Bangladesh. People use various spellings of the same word creating confusion for chat, social media posts, and other things. In this paper, we have developed a new way of transliterating Bangla to English using a phonetic approach. At first, we gathered 110,000 Bangla words from various sources. Then, we converted Bangla words into the International Phonetic Alphabet (IPA) to capture their sound. Subsequently, we converted IPA symbols into English letters using an IPA chart for English dialect. Then, we made modifications to some words based on certain rules proposed by our linguists keeping user-friendliness in mind. We also took experts’ advice on our transliterations to make sure these are correct and sound natural. Next, we developed a suggestion system where for one misspelled transliterated word, it will give n number of possible correct words. We wanted to have a proper balance of linguistical accuracy with user-friendliness. This data can help in language learning, computer programs that understand language, and working with digital text.