Generating Summaries through Selective Part of Speech Tagging

Abstract

The paper describes a new method for generating extractive summaries. The methodology is an unsupervised method and it employs a new linguistic method. It is based on using selective part of speech (PoS) tagging for significant unigrams and bigrams extraction. A new selective rule-based part of speech tagging system is developed that concentrates on the most important parts of speech for summarizations, such as noun, verb, adjective. Other parts of speech such as prepositions, articles, adverbs, etc., play a lesser role in determining the meaning of sentences; therefore, they are not considered when choosing significant unigrams and bigrams. The most significant unigrams and bigrams along with other features of a text are used to build a final summary. The proposed method is tested on Citations and Opinosis data sets (user reviews on selected topics). Results show that the proposed method performs better than Text-Rank, LexRank, and Edmundson summarization methods.