A statistical method for evaluating performance of part of speech tagger for Gujarati

Abstract

Part of Speech Tagging has continually been a difficult mission in the era of Natural Language Processing. This article offers POS tagging for Gujarati textual content the use of Hidden Markov Model. Using Gujarati text annotated corpus for training checking out statistics set are randomly separated. 80% accuracy is given by model. Error analysis in which the mismatches happened is likewise mentioned in element.