Özet:

Abstract Objectives: To develop a Neural Machine Translator which can be integrated to the chatting applications which will be helpful for the users who are convenient with their regional languages. Methods: Neural machine translation is an approach in machine translation which uses an artificial neural network to predict the likelihood of a sequence of words. It is typically modeling entire sentences in a single integrated model. NMT provides more accurate translation by taking into account the context in which a word is used, rather than just translating each individual word on its own. Findings: We used LSTM to build our model and we were able to get the Hindi sentences for the corresponding English sentences which contains the words count less than are equal to 5 accurately. We were getting translation for sentences more than 5 words also but not all. Like if we test for 100 sentences having more than 5 words, we got almost 75 to 80 sentences accurately.

Anahtar Kelimeler: