Transliterated Search of Hindi Lyrics

A huge number of Indian languages are written using native scripts. However, usually the websites and the user generated content (such as tweets, chats and blogs) in these languages are written using Roman script due to various phonetic-typing as the users feel comfortable in writing in their native language. Transliteration of many languages into Roman script is used copiously on the web not just for documents but also for user queries that are used to search these documents. A challenge that search engines face while processing transliterated queries and documents is that of extensive spelling variation. The aim of this topic is to systematically formalize several research problems that one must solve to tackle this unique situation prevalent in Web search for users of many languages around the world. We choose to solve the problem of Language identification when the Hindi words are written in Roman script. Then, transliterate the roman scripted Hindi words into Devanagri form. And when a search query is given, results should be retrieved for Hindi song lyrics