NLP-reliant Neural Machine Translation techniques used in smart city applications

Abstract

For smart city applications, Neural Machine Translation (NMT) methods based on Natural Language Processing (NLP) are crucial as they facilitate information sharing and communication among diverse populations. NLP techniques are used in many domains related to smart cities, such as development and research, business, industries, media, healthcare, and residences and communities. The majority of people in India communicate using their regional languages. The majority of applications used by users in smart cities will mostly accept English as input. These people will be able to interact with these smart city devices in their native tongues more effectively with the help of effective machine translation. Just 10% of Indians use English as their primary language of communication; there are 22 official regional languages in India. So, there is a requirement for better machine translation using natural language processing (NLP). Natural language processing for Indian regional languages has a very long way to go until it surpasses the abilities of existing rich NLP applications and techniques for the English language. Machine Translation is a technique of Natural Language Processing (NLP) that provides better inter-lingual communication. For low-resourced Indian languages, effective machine translation systems became important for establishing proper communication. Machine transliteration is a technique to convert source language into target language using a machine. The developed system takes the English language as input and then applies machine translation techniques to translate the source language into multiple languages using a trained RNN model and a multilingual search model that search the input word across all the datasets and generate the output into other Indian languages such as Hindi and Tamil. Our approach achieves top performance for the English-Hindi language pair and comparable results for other cases.