부산대학교 도서관

One of the most fundamental uses of machine learning is Machine Language Translation. There has been a lot of compelling research in this field. With the increase in the popularity of Large Language Models (LLMs) and their ever-increasing use cases, their application in machine language translation is immense. With the advancement in science and technology, the power of a Large Language model is growing to a point where it can actually replace humans at certain tasks. LLMs like Chat GPT are one the most powerful tools that exist. This paper provides a comparative study between Chat GPT and models like LSTM and T5 for Machine Language Translation. This paper focuses on English to Hindi translation. The primary idea is to fine-tune the Chat GPT model, 3.5-turbo, and compare its performance against other algorithms. A dataset from IIT Bombay would be used to fine-tune Chat GPT and other models.