Identification of Rules for Recognition of Named Entity Classes in Mizo Language

Abstract

Named Entity Recognition (NER) is a subtask of information extraction and known as entity identification, chunking, and extraction of classes. In this paper, we investigate the importance of Named Entities (NE) for Indian languages. We also give extra care for identification of rules for named entity classes in Mizo language. Named entity classes like person name, organization name, location name, designation, etc., is identified from a news corpus. An algorithm is developed for determining the rules for recognizing of NEs, and these rules are also compared with other Indian languages. Finally, it is tested over a small dataset and issues related to ambiguity in rules is also addressed.