Fuzzy Logic Based Method for Improving Text Summarization

TL;DR

This paper introduces a fuzzy logic-based method for extractive text summarization that improves summary quality by better sentence selection, validated on DUC2002 dataset with superior precision, recall, and F-measure.

Contribution

The paper proposes a novel fuzzy logic approach to enhance sentence weighting in extractive summarization, outperforming baseline and Microsoft Word 2007 methods.

Findings

Fuzzy logic method achieved higher precision, recall, and F-measure.

Experimental results on DUC2002 dataset validate effectiveness.

Fuzzy approach improves sentence selection quality.

Abstract

Text summarization can be classified into two approaches: extraction and abstraction. This paper focuses on extraction approach. The goal of text summarization based on extraction approach is sentence selection. One of the methods to obtain the suitable sentences is to assign some numerical measure of a sentence for the summary called sentence weighting and then select the best ones. The first step in summarization by extraction is the identification of important features. In our experiment, we used 125 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 text summarization based on fuzzy logic to improve the quality of the summary created by the general statistic method. We compare our results with the baseline summarizer and Microsoft Word 2007 summarizers. The results show that the best average precision, recall, and f-measure for the summaries were obtained by fuzzy method.