Language-independent extractive automatic text summarization based on automatic keyword extraction. (January 2022)

• Record Type: Journal Article
• Authors: Hernández-Castañeda, Ángel; García-Hernández, René Arnulfo; Ledeneva, Yulia; Millán-Hernández, Christian Eduardo
• Is Part Of: Computer speech & language. Volume 71(2022)
• Publication Date: 2022-01
• Subjects: Automatic summarization -- Genetic algorithm -- Topic modeling -- Extractive summaries -- Keywords; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2021.101267
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract: This study proposes a language and domain independent approach for automatic extractive text summarization (EATS) tasks, which is based on a clustering scheme supported by a genetic algorithm (GA), to find an optimal grouping of sentences. Furthermore, our approach includes a topic modeling algorithm to find the key sentences in clusters based on automatically generated keywords. Our experimental results show that our system outperforms previous methods through the application of two general steps: clustering, which helps to increase coverage, and the addition of semantic information to the model, which facilitates the detection of the key sentences in the clusters and improves precision. Highlights: A new approach to the automatic extractive text summary (EATS) system. Generation of a new language-independent approach to EATS. Generation of a new domain-independent approach to EATS. An EATS system that incorporates an evolutionary scheme and semantic information.