Approach of English to Sanskrit machine translation based on case-based reasoning, artificial neural networks and translation rules

Abstract

In Machine Translation (MT), we reuse past translation that is encoded into a set of cases, where case is the input sentence and its corresponding translation. A case which is similar to the input sentence will be retrieved and a solution is produced by adapting its target language. The CBR approach of MT is used as a learning technique in the domain of MT of English to Sanskrit language. In our approach, syntactical feature of English language is part of the cases in the case base. The new input English sentence is matched with old cases from the stored case bases using ANN method. The retrieved case is adapted using rules. In this paper, we present the integration of CBR approach of MT with ANN and rule-based model of English to Sanskrit MT, where CBR approach of MT is used for selection of Sanskrit translation rule of input English sentence.