Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization

Abubakar Bashir; Abdulkadir Abubakar Bichi

doi:10.35377/saucis...1853948

Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization

Abstract

Long-document extractive summarisation presents persistent challenges, including high redundancy, diffuse topical structure, and limited availability of high-quality supervision. Existing unsupervised graph-based methods improve upon classical centrality algorithms but rely on iterative ranking procedures that are sensitive to graph density and lack formal optimality guarantees. This paper introduces a fully unsupervised extractive summarisation framework in which sentence salience is formulated as a convex energy minimization problem over a semantic-similarity graph. The objective combines a centrality-driven prior with graph Laplacian regularisation, enabling joint inference of sentence importance while preserving convexity and admitting a closed-form solution via a single linear system solve. Discrete sentence selection is performed using a salience threshold, followed by a cosine-similarity-based redundancy filter in a separate greedy stage, preserving the tractability and global optimality of the inference step. Experiments on GovReport, BillSum, and PubMed demonstrate consistent improvements in ROUGE-1 over classical graph-based baselines, indicating improved unigram content coverage. Performance on ROUGE-2 and ROUGE-L is competitive with recent unsupervised approaches on some datasets but shows gaps on others, most notably in ROUGE-L on BillSum, which we attribute to the redundancy filter's effect on local sentence-level coherence. Sensitivity analyses confirm stability across a broad range of graph regularisation strengths and sparsity thresholds. These results support convex energy-based modeling as a principled, reproducible, and domain-independent alternative to heuristic iterative ranking for unsupervised long-document summarisation, while also identifying local coherence preservation as a direction for future improvement.

Keywords

References

N. Alami, M. E. Mallahi, H. Amakdouf, H. Qjidaa, Hybrid method for text summarization based on statistical and semantic treatment, Multimedia Tools and Applications, 80(13) (2021), 19567–19600. https://doi.org/10.1007/s11042-021-10613-9
A. S. Bashir, A. A. Bichi, U. Mahmud, A. M. Bello, Long-Text Abstractive Summarization using Transformer Models: A Systematic Review, Journal of the Brazilian Computer Society, 31(1) (2025), 1264–1279.
I. Beltagy, M. E. Peters, A. Cohan, Longformer: The Long-Document Transformer (No. arXiv:2004.05150), arXiv, 2020. https://doi.org/10.48550/arXiv.2004.05150
R. Cardenas, M. Galle, S. B. Cohen, On the Trade-off between Redundancy and Local Coherence in Summarization, Journal of Artificial Intelligence Research, 80 (2024), 273–326. https://doi.org/10.1613/jair.1.15191
A. Cohan, F. Dernoncourt, D. S. Kim, T. Bui, S. Kim, W. Chang, N. Goharian, A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 615–621, 2018. https://doi.org/10.18653/v1/N18-2097
Y. Dong, A. Mircea, J. C. K. Cheung, Discourse-Aware Unsupervised Summarization for Long Scientific Documents, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 1089–1102, 2021. https://aclanthology.org/2021.eacl-main.93
G. Erkan, D. R. Radev, LexRank: Graph-based Lexical Centrality as Salience in Text Summarization, Journal of Artificial Intelligence Research, 22 (2004), 457–479. https://doi.org/10.1613/jair.1523
D. Gillick, B. Favre, A Scalable Global Model for Summarization, In J. Clarke & S. Riedel (Eds.), Proceedings of the Workshop on Integer Linear Programming for Natural Language Processing (pp. 10–18), Association for Computational Linguistics, 2009. https://aclanthology.org/W09-1802/

T. Gokhan, P. Smith, M. Lee, GUSUM: Graph-based Unsupervised Summarization Using Sentence Features Scoring and Sentence-BERT, In D. Ustalov et al. (Eds.), Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing (pp. 44–53), Association for Computational Linguistics, 2022. https://aclanthology.org/2022.textgraphs-1.5/
N. Gu, E. Ash, R. Hahnloser, MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes, In S. Muresan, P. Nakov, & A. Villavicencio (Eds.), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 6507–6522), Association for Computational Linguistics, 2022. https://doi.org/10.18653/v1/2022.acl-long.450
L. Huang, S. Cao, N. Parulian, H. Ji, L. Wang, Efficient Attentions for Long Document Summarization, in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Association for Computational Linguistics, Online, 2021, pp. 1419–1436. https://doi.org/10.18653/v1/2021.naacl-main.112
Y.-H. Huang, H.-Y. Lan, Y.-S. Chen, Unsupervised Text Summarization of Long Documents using Dependency-based Noun Phrases and Contextual Order Arrangement, In Y.-C. Chang & Y.-C. Huang (Eds.), Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022) (pp. 15–24), ACLCLP, 2022. https://aclanthology.org/2022.rocling-1.3/
D. Jain, M. D. Borah, A. Biswas, Summarization of legal documents: Where are we now and the way forward, Computer Science Review, 40 (2021), 100388. https://doi.org/10.1016/j.cosrev.2021.100388
H. Y. Koh, J. Ju, M. Liu, S. Pan, An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics, ACM Computing Surveys, 55(8) (2023), 1–35. https://doi.org/10.1145/3545176
A. Kornilova, V. Eidelman, BillSum: A Corpus for Automatic Summarization of US Legislation, In L. Wang, J. C. K. Cheung, G. Carenini, & F. Liu (Eds.), Proceedings of the 2nd Workshop on New Frontiers in Summarization (pp. 48–56), Association for Computational Linguistics, 2019. https://doi.org/10.18653/v1/D19-5406
M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O. Levy, V. Stoyanov, L. Zettlemoyer, BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (No. arXiv:1910.13461), arXiv, 2020. https://doi.org/10.48550/arXiv.1910.13461
X. Liang, J. Li, S. Wu, J. Zeng, Y. Jiang, M. Li, Z. Li, An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks (No. arXiv:2208.08253), arXiv, 2022. https://doi.org/10.48550/arXiv.2208.08253
C.-Y. Lin, ROUGE: A Package for Automatic Evaluation of Summaries, Text Summarization Branches Out, (2004), 74–81. https://aclanthology.org/W04-1013/
Y. Liu, K. Shi, K. S. He, L. Ye, A. R. Fabbri, P. Liu, D. Radev, A. Cohan, On Learning to Summarize with Large Language Models as References (No. arXiv:2305.14239), arXiv, 2023. http://arxiv.org/abs/2305.14239
R. Mihalcea, P. Tarau, TextRank: Bringing Order into Text, In D. Lin & D. Wu (Eds.), Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (pp. 404–411), Association for Computational Linguistics, 2004. https://aclanthology.org/W04-3252/
M. Zaheer, G. Guruganesh, A. Dubey, J. Ainslie, C. Alberti, S. Ontanon, P. Pham, A. Ravula, Q. Wang, L. Yang, A. Ahmed, Big Bird: Transformers for Longer Sequences (No. arXiv:2007.14062), arXiv, 2021. https://doi.org/10.48550/arXiv.2007.14062
H. Zhang, X. Liu, J. Zhang, HEGEL: Hypergraph Transformer for Long Document Summarization, In Y. Goldberg, Z. Kozareva, & Y. Zhang (Eds.), Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (pp. 10167–10176), Association for Computational Linguistics, 2022. https://doi.org/10.18653/v1/2022.emnlp-main.692
Y. Zhang, A. Ni, Z. Mao, C. H. Wu, C. Zhu, B. Deb, A. H. Awadallah, D. Radev, R. Zhang, Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents (No. arXiv:2110.10150), arXiv, 2022. https://doi.org/10.48550/arXiv.2110.10150
H. Zheng, M. Lapata, Sentence Centrality Revisited for Unsupervised Summarization, In A. Korhonen, D. Traum, & L. Márquez (Eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 6236–6247), Association for Computational Linguistics, 2019. https://doi.org/10.18653/v1/P19-1628

Details

Primary Language

English

Subjects

Natural Language Processing

Journal Section

Research Article

Authors

Abubakar Bashir ^*
0000-0002-4346-6826
Nigeria

Abdulkadir Abubakar Bichi
0000-0002-5872-8315
Nigeria

Early Pub Date

June 19, 2026

Publication Date

June 30, 2026

Submission Date

January 1, 2026

Acceptance Date

April 25, 2026

Published in Issue

Year 2026 Volume: 9 Number: 3

DOI

https://doi.org/10.35377/saucis...1853948

IZ

https://izlik.org/JA96PT96LJ

Cite

RIS / Bibtex

APA

Bashir, A., & Abubakar Bichi, A. (2026). Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization. Sakarya University Journal of Computer and Information Sciences, 9(3), 754-764. https://doi.org/10.35377/saucis...1853948

AMA

1.Bashir A, Abubakar Bichi A. Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization. SAUCIS. 2026;9(3):754-764. doi:10.35377/saucis.1853948

Chicago

Bashir, Abubakar, and Abdulkadir Abubakar Bichi. 2026. “Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization”. Sakarya University Journal of Computer and Information Sciences 9 (3): 754-64. https://doi.org/10.35377/saucis. 1853948.

EndNote

Bashir A, Abubakar Bichi A (June 1, 2026) Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization. Sakarya University Journal of Computer and Information Sciences 9 3 754–764.

IEEE

[1]A. Bashir and A. Abubakar Bichi, “Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization”, SAUCIS, vol. 9, no. 3, pp. 754–764, June 2026, doi: 10.35377/saucis...1853948.

ISNAD

Bashir, Abubakar - Abubakar Bichi, Abdulkadir. “Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization”. Sakarya University Journal of Computer and Information Sciences 9/3 (June 1, 2026): 754-764. https://doi.org/10.35377/saucis. 1853948.

JAMA

1.Bashir A, Abubakar Bichi A. Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization. SAUCIS. 2026;9:754–764.

MLA

Bashir, Abubakar, and Abdulkadir Abubakar Bichi. “Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 3, June 2026, pp. 754-6, doi:10.35377/saucis. 1853948.

Vancouver

1.Abubakar Bashir, Abdulkadir Abubakar Bichi. Energy-Based Interaction-Aware Graph Modeling for Unsupervised Long-Document Extractive Summarization. SAUCIS. 2026 Jun. 1;9(3):754-6. doi:10.35377/saucis. 1853948