Automatic Named Entity Identification and Classification using Heuristic Based Approach for Telugu
P. M. Yohan, B. Sasidhar, Hussain Basha, Aliseri Govardhan · 2014
Named Entity Recognition (NER) and Classification becomes more and more important in many natural language processing applications. It helps machine to recognize named entities in text and assign them with the appropriate categories. NER for Telugu is a challenging task since Telugu is very rich in morphology. Recent systems rely on machine learning approaches, but their performance is highly dependent on size and quality of training data. In this paper we proposed a rule based Named Entity Recognition and Classification system for Telugu language. In this paper we describe the identification and classification of Named Entities using word level features, work lookup features and contextual features. Further classification of identified Named Entities and ambiguity resolution is done through contextual rules and syntax information. The System is tested on different data sets of News paper and Teluguwiki corpus.