Novel Technique for Script Translation using NLP: Performance Evaluation
Darshana Patil, S. B. Chaudhari, Sharmila Shinde · 2021 International Conference on Emerging Smart Computing and Informatics (ESCI) · 2021
Data can be represented in various languages, such as Hindi, Marathi and English in social media and also in various knowledge resources. The data is open to users in a different format. Information comprehension is very difficult for uneducated individuals. Often it is difficult for people to read or comprehend meaningful data available on social media. Thus, researchers used NLP to develop different machine translation techniques, such as rule-based, statistical-based and some hybrid machine translation. Natural language is incredibly rich in form and composition and highly vague. Natural language comprehension is much harder compared to natural language development. We present the MVET (Marathi video to English Text translation) technique in this research manuscript which helps to translate Marathi Video content into English text format. That will be very useful for people who really aren't Marathi. Sometimes so many people have lost valuable information because of the regional language crisis. We have developed the MVET machine translation technique to solve this problem, which will achieve more precision compared to existing methods such as statistical, rule-based and hybrid.