A Hybrid Optimization Approach for Neural Machine Translation Using LSTM+RNN with MFO for Under Resource Language (Telugu)

NMT (Neural Machine Translation) is an innovative approach in the field of machine translation, contrast to SMT (statistical translation) and Rule-based techniques which has resulted annotable improvements. This because able overcome many shortcomings that are inherent traditional approaches. The Development grown tremendously recent years but performance remain under optimal when applied low resource language pairs like Telugu, Tamil Hindi. In this work a proposedmethod fortranslating (Telugu English) attempted, enhancesthe accuracy execution time period.A hybrid method utilizing Long short-term memory (LSTM) Recurrent Neural Network (RNN) used for testing training dataset. event long-range dependencies, LSTM will generate more accurate results than standard RNN would endure technique enhances LSTM. during encoding decoding phases NMT. Moth Flame Optimization (MFO) utilized proposed system purpose providing encoder decoder model with best ideal points data.