Assessing shallow sentence scoring techniques and combinations for single and multi-document summarization. (15th December 2016)

• Record Type: Journal Article
• Authors: Oliveira, Hilário; Ferreira, Rafael; Lima, Rinaldo; Lins, Rafael Dueire; Freitas, Fred; Riss, Marcelo; Simske, Steven J.
• Is Part Of: Expert systems with applications. Volume 65(2016)
• Page Start: 68
• Page End: 86
• Publication Date: 2016-12-15
• Subjects: Automatic text summarization -- Extractive-based approaches -- Sentence scoring techniques -- Single-document summarization -- Multi-document summarization; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2016.08.030
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We investigate eighteen shallow sentence scoring techniques and ensemble strategies. Experiments were performed in several datasets for single- and multi-document task. Ensemble strategies lead to improvements over the individual scoring techniques. Ensembles that perform competitively against the state-of-the-art were identified. Abstract: The volume of text data has been growing exponentially in the last years, mainly due to the Internet. Automatic Text Summarization has emerged as an alternative to help users find relevant information in the content of one or more documents. This paper presents a comparative analysis of eighteen shallow sentence scoring techniques to compute the importance of a sentence in the context of extractive single- and multi-document summarization. Several experiments were made to assess the performance of such techniques individually and applying different combination strategies. The most traditional benchmark on the news domain demonstrates the feasibility of combining such techniques, in most cases outperforming the results obtained by isolated techniques. Combinations that perform competitively with the state-of-the-art systems were found.