Language Model Based Related Word Prediction from an Indian Epic-Mahabharata

The “Mahabharata” is the most well-known of several Indian works of literature that are mentioned in numerous contexts for quite varied reasons. This literature itself has a variety of dimensions and elements that benefit people in both their careers and personal lives. Sanskrit was the original language used to write this Indian epic. Thanks to advancements in areas such as Natural Language Processing, Intelligent Systems, Machine Learning, and Human-Computer Interaction, this content can be processed in accordance with the domain's requirements. The difficulty that people have when analysing the Mahabharata is that they cannot help but have an emotional reaction to the story being told. It is intriguing to analyze this book and get insightful knowledge from the Mahabharata. In addition, the human brain is incapable of memorizing statistical or computational data, such as how frequently two words occur together in a phrase. The average sentence length in all of literature? What is the problem with the terms utilized throughout phrases, and which word appears most frequently in the text? Therefore, in this research, provide an NLP pipeline to obtain some mathematical and statistical findings as well as the most pertinent word-searching technique from the epic “Mahabharata.” To identify the best outcomes that may be applied further in the numerous domains where Mahabharata has to be referred to, layered the textual algorithms.