Named Entity Recognition using Machine learning techniques for Telugu language

Abstract

In this paper, we depict hybrid approach, i.e., combination of rule based approach and machine learning techniques, i.e Conditional Random Fields (CRF) for Named Entity Recognition (NER). The main objective of Named Entity Recognition is to categorize all Named Entities (NE) in a document into predefined classes like Person name, Location name, Organization name. This paper first outlines the Named Entity Recognizer using rule based approach. In this approach we prepared Gazette lists for names of persons, locations and organizations, some suffix and prefix features and dictionary consist of 200000 words to recognize the category of names entities. Further, we used Machine learning technique, i.e., CRF in order to improve the accuracy of the system.