A Comprehensive Guide to Natural Language Processing in Sanskrit with Named Entity Recognition

Abstract

Named Entity Recognition (NER) is a technique for recognizing and categorizing certain entities from a file or image, such as names, locations, organizations, numbers, and others. Named Entity Recognition (NER) is used in Natural Language Processing (NLP) to ease text extraction. This method is widely used in automated text processing in a wide range of enterprises, as well as in academic research, artificial intelligence, robotics, and bioinformatics.Previously, named entity recognition (NER) research focused on handwritten rules; however, machine learning models such as Hidden Markov Model (HMM), Maximum Entropy (MaxEnt), Maximum Entropy Markov model (MEMM), Support Vector Machine (SVM), Conditional Random Fields (CRFs) are now used to develop NER systems. The goal of concentrating on Sanskrit is to establish its applicability, examine its structure, and utilize accurate Named Entity Recognition methods. This study presents a breakdown of several strategies used for Named Entity Recognition (NER) in Sanskrit, such as rule-based methods, machine learning methods, and hybrid methods that incorporate both approaches. The study explores and contrasts the issues of named entity recognition (NER) for the Sanskrit language using conventional evaluation measures such as accuracy, precision, recall, and F-measure.