Feature Priority Based Sentence Filtering Method for Extractive Automatic Text Summarization

Abstract

Abstract Due to increasing amount of text data available on internet it becomes difficult for users to get the desired information quickly. In order to reduce this access time a summary could be utilized generated using Automatic Text Summarization. In general it could be extractive or abstractive. For extractive text summarization in which representative sentences from the document itself are selected as summary, various statistical, knowledge based and discourse based methods are proposed by researchers. In this paper we explored feature based extractive approaches for text summarization. We proposed a feature priority based filtering method for summarization. For this purpose we used sentence location as main feature and other features in priority to filter the redundant sentences. Experimental results on DUC2002 datasets shows that our method performs uniformly as compared to the best results for particular combination of features.