Sanskrit Language Enconversion to Universal Networking Language UNL

Abstract

Machine Translation (MT) has been the prime research area in last few decades. Researchers newlinefrom different domains like statistics, linguistics, mathematics, artificial intelligence and newlinephilosophy have been witnessed to work on solving various problems related to MT. Several newlinemethodologies have been used by researchers to develop MT systems for different languages. newlineDeveloping MT system based on Universal Networking Language (UNL) is also an effort in newlinethe direction of MT field. UNL was first launched in 1996 by United Nations University newline(UNU) at Institute of Advanced Studies, Tokyo Japan. Key components of UNL for natural newlinelanguage processing are EnConverter and DeConverter. The first component is used to newlineconvert the Natural Language (NL) sentence into equivalent UNL statements and the second newlinecomponent performs the reverse operation i.e. generates the NL from UNL expressions. The newlinefocus of the research work carried out in this thesis is on the development of Enconverter newlinesystem for Sanskrit language. newlineThe thesis starts with introduction part which provides information about the importance of newlinemachine translation in today s multilingual world, Sanskrit language structure, UNL system, newlineneed of MT, problems faced during MT development and the comparison of UNL with other newlinesystems. This work also highlights a comprehensive survey of MT approaches, existing newlineMT systems, linguistic tools, data repositories and MT platforms. Among the available newlineresearch in machine translation system, it is found that a little work has been done by the newlineresearchers for Sanskrit language MT development. The work that has been done, does not newlinetake care of application of neural network for designing stemmer, tagger, parser as well as newlinetranslator for developing Sanskrit MT system. Further keeping in mind the research gaps newlinefrom the survey there is a need to develop a new Sanskrit MT system which could perform newlinetranslation in multiple languages simultaneously with less effort.