Automatic Text Summarization: A Review of Approaches, Challenges, and Future Directions
Journal of Computer Science and Technology · 22.10.2025 · 25 (2) · e08
DOI: 10.24215/16666038.25.e08 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science and Technology, online erschienen am 22.10.2025. Verfasst von Sara Zayed und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Automatic text summarization (ATS) is a critical area in natural language processing that aims to condense long documents into concise and meaningful summaries. Manual text summarization is a time-consuming, labor-intensive, and costly process. Researchers have been actively working to enhance ATS techniques, focusing on either extractive, abstractive, or hybrid methods. This review explores different summarization techniques, including extractive and abstract approaches, with a focus on recent developments using machine learning and deep learning models. The paper also discusses the challenges in generating high-quality summaries, including coherence, redundancy, and information loss. Finally, this review provides a comprehensive survey for researchers, presenting the various aspects of ATS, including approaches, taxonomy analysis, datasets, evaluation methods, and future research trends.
Zitieren
APA
Zayed, S., Ezzat, M., & Hefny, H. A. (2025). Automatic Text Summarization: A Review of Approaches, Challenges, and Future Directions. Journal of Computer Science and Technology, 25(2), e08. https://doi.org/10.24215/16666038.25.e08
Vancouver
Zayed S, Ezzat M, Hefny HA. Automatic Text Summarization: A Review of Approaches, Challenges, and Future Directions. Journal of Computer Science and Technology. 2025;25(2):e08. doi:10.24215/16666038.25.e08
BibTeX
@article{Zayed2025,
author = {Zayed, Sara and Ezzat, Mostafa and Hefny, Hesham A.},
title = {Automatic Text Summarization: A Review of Approaches, Challenges, and Future Directions},
journal = {Journal of Computer Science and Technology},
year = {2025},
volume = {25},
number = {2},
pages = {e08},
doi = {10.24215/16666038.25.e08}
}
EUVIMED