Word-sentence co-ranking for automatic extractive text summarization. (15th April 2017)

• Record Type: Journal Article
• Authors: Fang, Changjian; Mu, Dejun; Deng, Zhenghong; Wu, Zhiang
• Is Part Of: Expert systems with applications. Volume 72(2017)
• Page Start: 189
• Page End: 195
• Publication Date: 2017-04-15
• Subjects: Automatic summarization -- Extractive summary -- Sentence scoring -- Pagerank -- Unsupervised learning; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2016.12.021
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A principled word-sentence co-ranking model called CoRank is proposed. The convergence of CoRank with matrix notation is proved. A redundancy elimination technique is presented to further improve the performance of CoRank. Abstract: Extractive summarization aims to automatically produce a short summary of a document by concatenating several sentences taken exactly from the original material. Due to its simplicity and easy-to-use, the extractive summarization methods have become the dominant paradigm in the realm of text summarization. In this paper, we address the sentence scoring technique, a key step of the extractive summarization. Specifically, we propose a novel word-sentence co-ranking model named CoRank, which combines the word-sentence relationship with the graph-based unsupervised ranking model. CoRank is quite concise in the view of matrix operations, and its convergence can be theoretically guaranteed. Moreover, a redundancy elimination technique is presented as a supplement to CoRank, so that the quality of automatic summarization can be further enhanced. As a result, CoRank can serve as an important building-block of the intelligent summarization systems. Experimental results on two real-life datasets including nearly 600 documents demonstrate the effectiveness of the proposed methods.