Efficient Extractive Text Summarization Using BiLSTM, Hypergraph, and Dominating Set Property

Abstract

Automatic text summarization condenses voluminous text while preserving crucial information. Despite significant advancements in this field, challenges persist in accurately identifying key content, maintaining contextual coherence, and ensuring computational efficiency. The existing approaches struggle to effectively capture global relationships between sentences and minimize redundancy. In this study, we propose an extractive text summarization framework using Bidirectional Long Short-Term Memory with a hypergraph and a dominating set mechanism. A neural encoding module derives context-aware sentence embeddings, and a hypergraph-based representation models higher-order relational dependencies among sentences. A dominating set-based selection strategy is then applied to identify the most informative sentences for summary generation. The proposed model is evaluated using the CNN/Daily Mail dataset and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics. Empirical evaluation attains ROUGE-1, ROUGE-2, and ROUGE-L scores of 0.4221, 0.3563, and 0.3901, respectively, and demonstrates the proposed model’s capability to effectively capture key content and generate coherent and informative summaries. The proposed framework proves to be an efficient approach to automatic summarization and has the potential to be applied in journalism, healthcare, legal analysis, and digital content management. 

Received: 12 February 2026 | Revised: 8 June 2026 | Accepted: 23 June 2026

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of this study are openly available in Kaggle at https://www.kaggle.com/datasets/gowrishankarp/newspaper-text-summarization-cnn-dailymail/data1. 

Author Contribution Statement

Pradeepa Sampath: Conceptualization, Methodology, Software, Data curation, Writing – original draft, Writing – review & editing, Project administration. Shrijaa Venkatasubramanian Subashini: Conceptualization, Methodology, Software, Data curation, Writing – original draft, Writing – review & editing. Vimal Shanmuganathan: Validation, Formal analysis, Investigation, Resources, Visualization, Supervision. Seifedine Kadry: Validation, Formal analysis, Investigation, Resources, Visualization, Supervision.