Experiments in Telugu NER: A Conditional Random Field Approach

Abstract

Named Entity Recognition(NER) is the task of identifying and classifying tokens in a text document into predefined set of classes. In this paper we show our experiments with various feature combinations for Telugu NER. We also observed that the prefix and suffix information helps a lot in finding the class of the token. We also show the effect of the training data on the performance of the system. The best performing model gave an Fb=1 measure of 44.91. The language independent features gave an Fb=1 measure of 44.89 which is close to Fb=1 measure obtained even by including the language dependent features.