Feature-based sentence extraction using fuzzy inference rules

Abstract

Automatic text summarization is a wide research area. Automatic text summarization is to compress the original text into a shorter version and help the user to quickly understand large volumes of information. There are several ways in which one can characterize different approaches to text summarization: extractive and abstractive from single document or multi document. This paper focuses on the automatic text summarization by sentence extraction. The first step in summarization by extraction is the identification of important features. Our approach used important features based on fuzzy logic to extract the sentences. In our experiment, we used 30 test documents in DUC2002 data set. Each document is prepared by preprocessing process: sentence segmentation, tokenization, removing stop word, and word stemming. Then, we use 8 important features and calculate their score for each sentence. We propose a method using fuzzy logic for sentence extraction and compare our results with the baseline summarizer and Microsoft Word 2007 summarizers. The results show that the highest average precision, recall, and F-measure for the summaries are conducted from fuzzy method.