English to tamil transliteration by Machine learning

Abstract

As multilingual documents are abundantly available on the Internet, there is a great demand to bridge the Language barrier. Accessing information available in varied languages is a challenge and machine translation is one of the solutions. For multilingual country like India, a scheme for automatically translating between the languages is very desirable for social and political interaction. Recently, there has been an enormous boom in Machine Translation research and a paradigm shift away from rule-based methods towards data-driven methods in Machine Translation. In applications such as machine translation, cross-lingual information retrieval, multi lingual text and speech processing, there is an increasing need to translate out-of-vocabulary words from one language to another. Proper noun processing plays an important role in query translation during cross-language information retrieval, where the query is specified in a language different from that of the documents to be retrieved. One of the major issues that need to be considered by translators is translating named entities such as person, location, organization names and technical terms. During machine translation, the most proper way to handle named entities is to transliterate them into the target language by closely preserving their phonetic structure. Thus machine transliteration is an important and challenging task and has gained prime importance as a supporting tool for Machine translation and cross language information retrieval especially when proper names and technical terms are involved. The performance of machine translation and cross-language information retrieval depends extremely on accurate transliteration of named entities. Hence there is a need for an efficient transliteration model that must aim to preserve the phonetic structure of words as closely as possible during transliteration. ...