Named Entity Recognition for Indic Languages: A Comprehensive Survey

The rapid proliferation of digital content in Indic languages has necessitated the development of high-level natural language processing (NLP) techniques. Among these, Named Entity Recognition (NER) emerges as a pivotal technique for the extraction of valuable information from unstructured textual data. This survey paper provides a exhaustive overview of contemporary NER approaches specifically designed for Indic languages, with a particular focus on the identification of commonly used effective methods for the NER task. Through a systematic analysis of existing methodologies, the paper categorizes and evaluates various strategies, investigates the application of diverse machine learning models, and underscores the fundamental importance of NER within the broader domain of NLP. Recognizing the unique linguistic and contextual characteristics inherent to Indie languages, the paper delves into the challenges posed by their rich morphology, intricate syntax, and diverse writing systems. Furthermore, the paper critically examines existing eval-uation metrics and datasets, identifies recent advancements and trends in the eld, and explores the practical implications and potential impact of accurate Indic NER. By addressing current limitations, identifying open questions, and proposing directions for future research, this research aims to advance the creation of reliable and efficient Named Entity Recognition (NER) systems tailored to the extensive and varied world of Indic languages.