AUTOMATIC TEXT SUMMARIZATION AND DEADWOOD REMOVAL FOR PUNJABI LANGUAGE

Due to large information over the internet it becomes very difficult and laborious task to get the useful information. Automatic text summarization is one of the techniques which give the shorthand information which is half as the original text. This paper proposes the system to generate summary by using differen t features and the by applying the deadwood rules. Deadwood is the words or phrases in the sentence which can be omitted without losing its original meaning. The first step is Pre - Processing using segmentation, tokenization and stop word removal. After tha t deadwood rules are implemented to shorten the text and then score is calculated over the seventeen features. In last the highest scored sentences a re selected to form the summary