Bridging the Language Gap: Enhancing English-to-Telugu Translation using NMT and Encoding Decoding Techniques

Language translation, particularly in the context of natural language processing, involves converting text or speech from one language into another while preserving its meaning, context, and cultural nuances. This task is critical for enabling communication across different languages and is a significant area of research and development in artificial intelligence. Machine translation has a wide range of real-time applications that have significantly impacted various fields by bridging language barriers. Some of the real time application includes Google Translate, Microsoft Translator, Skype Translator. NMT has revolutionized language translation with models like Google’s Transformer, OpenAI’s GPT, Facebook’s BART, and Google’s T5. Development of a machine translation system to translate English sentences into Telugu. The system utilizes a neural network model based on an encoder-decoder architecture with attention mechanism. Preprocessing techniques are applied to the dataset, including lowercasing, removal of special characters, and tokenization. The sparse categorical cross-entropy loss function and Adam optimizer are used to train the model. The actual vs. projected output is used to evaluate performance. Pre-trained GloVe word embeddings are used in the implementation to improve the model’s capacity to extract semantic information.