Coreference Resolution in the Assamese Language: A Pioneering Attempt

Coreference resolution is the process of identifying all expressions in a text that refer to the same entities. It is an essential task in several Natural Language Processing (NLP) tasks to interpret the text properly. This is used in many sophisticated NLP tasks like machine translation, information extraction, document summarization, question answering, etc. It is a complex problem with numerous challenges and ramifications for linguistics and computation. There is limited work in Indic languages, and it is hardly found in Assamese languages. Our effort is one of the pioneering attempts in the Assamese coreference resolution that is reported in this paper.