English to Marathi Text Translation using Deep learning
Swati Shilaskar, Shivam Ghadge, Mugdha Dhopade, Janhvi Godle, Mihika Gulhane · 2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · 2022
In today’s times, though text translation has become a very easy task, translation to Indian local languages still has some technical issues to deal with. Thus, to avoid such irregularities a text translator is proposed. The work aims to translate text from English to Marathi with an improved efficiency and accuracy. Further, the paper reveals information regarding the role of Deep Learning and Natural Language Processing (NLP) in development of the Model. The input text goes through the process of tokenization. The processed data is sent to the encoder and decoder model where it undergoes through different layers. Embedding layers accept the text in English. The model makes use of Long Short-Term Memory (LSTM) for encoding the sequence of words. The model has testing accuracy of 90.66%.