A Review on the Punjabi Text Classification using Natural Language Processing

Abstract: Now-a-days, text classification is very necessary for an every field to organise the text documents. Till now there is no classifier available for classification of Punjabi documents. There are two new algorithms, one is ontology based and second is hybrid approach are proposed for Punjabi text classification. Here we have some Punjabi news article examples which we have to classify with the help of algorithms. Punjabi is a Indo Aryan language spoken in west Punjab (Pakistan) and East Punjab (India). So a little work has done in Punjabi text classification. The problem tackled by many Indian languages that is no capitalization, lack of standardization, spelling and scarcity of tools. Punjabi language has more inflectional forms than English language.

Keywords: Punjabi text classification, news articles, ontology based and hybrid approach.