ABSTRACTIVE SUMMARIZATION FOR INDONESIAN HUMAN TRAFFICKING COURT DECISIONS USING TRANSFORMER MODELS

Authors

DOI:

https://doi.org/10.33480/jitk.v11i4.8221

Keywords:

Abstractive Summarization, Court Decisions, Indonesian Legal Documents, Transformer Models, XSum Dataset

Abstract

Indonesian Supreme Court decisions on Human Trafficking (TPPO) are lengthy and structurally complex, rendering manual review inefficient for legal practitioners. Existing abstractive summarization research for Indonesian text concentrates on news and social media, while no publicly benchmarked XSum-style dataset exists for the Indonesian legal domain. This study has two explicit objectives: (i) an XSum-structured legal summarization dataset is constructed from 404 TPPO decisions, and (ii) four fine-tuned Transformer models (T5 Base Indonesia, mT5 Small, DistilBART CNN, BART Large XSum) are benchmarked against extractive and classical abstractive baselines. The method couples an n8n-based PDF extraction pipeline with CSV-sourced verdict statements as reference summaries, followed by fine-tuning and evaluation using ROUGE-1/2/L and BERTScore F1, complemented by paired bootstrap significance testing (n=10,000). Results show T5 Base Indonesia attains the highest ROUGE-L of 39.49 and BERTScore F1 of 74.82, while mT5 Small achieves the highest ROUGE-1 of 44.97, all significantly outperforming Seq2Seq+Attention (ROUGE-1 27.31) and First-2-Sentences (ROUGE-1 10.86) with p<0.001. The contributions are: an XSum-formatted TPPO dataset, an automated extraction pipeline, and a comprehensive benchmark spanning extractive, classical abstractive, and Transformer-based methods. These findings offer practical benefits for legal document analysis and judicial information retrieval in Indonesia.

Downloads

Download data is not yet available.

Author Biography

  • Galih Wasis Wicaksono, Universitas Muhammadiyah Malang

    Galih Wasis Wicaksono is a Lecturer (Lektor) in Informatics at Universitas Muhammadiyah Malang. He holds a Master of Computer Science from Universitas Gadjah Mada (2014) and a Professional Engineer degree from Universitas Muhammadiyah Malang (2021). His research interests include artificial intelligence for legal systems, learning management systems, computer vision, and knowledge management. He has led multiple research projects on AI-based court decision analysis, legal knowledge clustering, and educational technology innovation.

References

[1] H. Abo-Bakr and S. A. Mohamed, “Automatic multi-documents text summarization by a large-scale sparse multi-objective optimization algorithm,” Complex & Intelligent Systems, vol. 9, pp. 4629–4644, Feb. 2023, doi: 10.1007/s40747-023-00967-y.

[2] H. Y. Koh, J. Ju, M. Liu, S. Pan, and S. Pan, “An Empirical Survey on Long Document Summarization: Datasets, Models, and Metrics,” ACM Comput. Surv., vol. 55, no. 8, Aug. 2023, doi: 10.1145/3545176.

[3] M. F. Mridha, A. A. Lima, K. Nur, S. C. Das, M. Hasan, and M. M. Kabir, “A Survey of Automatic Text Summarization: Progress, Process and Challenges,” IEEE Access, vol. 9, pp. 156043–156070, 2021, doi: 10.1109/ACCESS.2021.3129786.

[4] M. Kirmani, G. Kaur, and M. Mohd, “Analysis of Abstractive and Extractive Summarization Methods,” International Journal of Emerging Technologies in Learning, vol. 19, no. 1, pp. 86–96, 2024, doi: 10.3991/ijet.v19i01.46079.

[5] N. Giarelis, C. Mastrokostas, and N. Karacapilidis, “Abstractive vs. Extractive Summarization: An Experimental Review,” Applied Sciences (Switzerland), vol. 13, no. 13, Jul. 2023, doi: 10.3390/app13137620.

[6] N. Sharma and S. Singh, “A Hybrid Extractive and Encoder-Decoder-Based Approach for Mitigating Hallucination in Automatic Text Summarization,” Journal of Transformative Technologies and Sustainable Development, vol. 9, p. 15, 2025, doi: 10.1007/s41314-025-00083-4.

[7] Z. Ji et al., “Survey of Hallucination in Natural Language Generation,” ACM Comput. Surv., vol. 55, no. 12, Dec. 2023, doi: 10.1145/3571730.

[8] Y. Song et al., “A Hybrid Summarization Model for Legal Judgment Document Based on Domain Knowledge,” Information Technology and Control, vol. 53, no. 3, pp. 772–784, 2024, doi: 10.5755/j01.itc.53.3.36602.

[9] A. Rao, S. Aithal, and S. Singh, “Single-Document Abstractive Text Summarization: A Systematic Literature Review,” ACM Comput. Surv., vol. 57, no. 3, Nov. 2024, doi: 10.1145/3700639.

[10] K. M. Rani Krishna, K. Somasundaram, P. Arulmozhivarman, S. A. Immanuel, and E. R. Rajkumar, “Deep learning for text summarization using NLP for automated news digest,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-20224-1.

[11] J. V. Alves, J. Liébana, H. Ferreira, and P. Bizarro, “SARSum: A Relevance and Comprehensiveness-Aware Abstractive Summarization Dataset for Suspicious Activity Reports,” in Frontiers in Artificial Intelligence and Applications, IOS Press BV, Oct. 2025, pp. 4065–4072. doi: 10.3233/FAIA251296.

[12] M. Heddaya, K. MacMillan, H. Mei, C. Tan, and A. Malani, “CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions,” in Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque: Association for Computational Linguistics, Apr. 2025, pp. 1917–1942. doi: 10.18653/v1/2025.findings-naacl.102.

[13] D. Datta, S. Soni, R. Mukherjee, and S. Ghosh, “MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments,” in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore: Association for Computational Linguistics, 2023, pp. 5291–5302. doi: 10.18653/v1/2023.emnlp-main.321.

[14] V. Zmiycharov, T. Tsonkov, and I. Koychev, “EurLexSummarization - A New Text Summarization Dataset on EU Legislation in 24 Languages with GPT Evaluation,” in Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024), Sofia: Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences, Sep. 2024, pp. 206–213. Accessed: Feb. 03, 2026. [Online]. Available: https://aclanthology.org/2024.clib-1.22/

[15] G. W. Wickasono, N. P. Hidayah, C. S. K. Aditya, A. F. P. Dewa, H. Fatikasari, M. A. P. Insani, M. H. F. Anwar, and N. A. Anhari, “Human Trafficking Court Decisions (Indonesia) — Structured Dataset,” Mendeley Data, vol. 1, 2025, doi: 10.17632/8gtbky7r9x.1.

[16] Y. Sunusi, N. Omar, and L. Qadri Zakaria, “Exploring Abstractive Text Summarization: Methods, Dataset, Evaluation, and Emerging Challenges,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 7, pp. 1307–1324, 2024, doi: 10.14569/IJACSA.2024.01507130.

[17] Supriyono, A. P. Wibawa, Suyono, and F. Kurniawan, “A survey of text summarization: Techniques, evaluation and challenges,” Natural Language Processing Journal, vol. 7, p. 100070, 2024, doi: 10.1016/j.nlp.2024.100070.

[18] K. Chaudhari, R. Mahale, F. Khan, S. Gaikwad, and K. Jadhav, “Comprehensive Survey of Abstractive Text Summarization Techniques,” International Research Journal on Advanced Engineering and Management, vol. 2, no. 7, Jul. 2024, doi: 10.47392/IRJAEM.2024.0323.

[19] Y. Xue, X. Cao, X. Yang, Y. Wang, R. Wang, and J. Li, “We Need to Talk About Reproducibility in NLP Model Comparison,” in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore: Association for Computational Linguistics, 2023, pp. 9424–9434. doi: 10.18653/v1/2023.emnlp-main.586.

[20] S. Casola, I. Lauriola, and A. Lavelli, “Pre-trained transformers: an empirical comparison,” Machine Learning with Applications, vol. 9, p. 100334, Sep. 2022, doi: 10.1016/j.mlwa.2022.100334.

[21] A. Belz, S. Agarwal, A. Shimorina, and E. Reiter, “A Systematic Review of Reproducibility Research in Natural Language Processing,” in A Systematic Review of Reproducibility Research in Natural Language Processing, Association for Computational Linguistics, 2021, pp. 381–393. doi: 10.18653/v1/2021.eacl-main.29.

[22] G. Hartawan, D. Sa’adillah Maylawati, and W. Uriawan, “Bidirectional and Auto-Regressive Transformer (BART) for Indonesian Abstractive Text Summarization,” Jurnal Informatika Polinema, vol. 10, no. 4, Aug. 2024, doi: 10.33795/jip.v10i4.5242.

[23] T. Hasan et al., “XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages,” in Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, Association for Computational Linguistics, 2021, pp. 4693–4703. doi: 10.18653/v1/2021.findings-acl.413.

[24] S. D. Atagong, H. Tonnang, K. Senagi, M. Wamalwa, and K. M. Agboka, “A review on knowledge and information extraction from PDF documents and storage approaches,” Front. Artif. Intell., vol. 8, 2025, doi: 10.3389/frai.2025.1466092.

[25] H. Zhang, P. S. Yu, and J. Zhang, “A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models,” ACM Comput. Surv., vol. 57, no. 11, Jun. 2025, doi: 10.1145/3731445.

[26] J. P. Tambusai, A. Maulana, N. Hafizhah Nst, N. Azahra, and Y. Lubis, “The Role of Punctuation In Clarifying Written Communication,” Jurnal Pendidikan Tambusai, vol. 9, no. 1, Jan. 2025, doi: 10.31004/jptam.v9i1.25038.

[27] M. Siino, I. Tinnirello, and M. La Cascia, “Is text preprocessing still worth the time? A comparative survey on the influence of popular preprocessing methods on Transformers and traditional classifiers,” Inf. Syst., vol. 121, p. 102342, Mar. 2024, doi: 10.1016/j.is.2023.102342.

[28] H. Bichri, A. Chergui, and M. Hain, “Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 2, May 2024, doi: 10.14569/IJACSA.2024.0150235.

[29] K. Hiniduma, S. Byna, and J. L. Bez, “Data Readiness for AI: A 360-Degree Survey,” ACM Comput. Surv., vol. 57, no. 9, Apr. 2025, doi: 10.1145/3722214.

[30] S. Yan, “Long Document Summarization with Transformer Models: A Comparative Evaluation on the Gutenberg Dataset,” in Proceedings of 2025 6th International Conference on Computer Information and Big Data Applications, CIBDA 2025, Association for Computing Machinery, Inc, Aug. 2025, pp. 203–210. doi: 10.1145/3746709.3746746.

[31] Y. Sunusi, N. Omar, and L. Q. Zakaria, “Enhanced transformer for lengthcontrolled abstractive summarization based on summary output area,” PeerJ Comput. Sci., vol. 11, 2025, doi: 10.7717/peerj-cs.2667.

[32] R. Alsultan, A. Sagheer, H. Hamdoun, L. Alshamlan, and L. Alfadhli, “PEGASUS-XL with saliency-guided scoring and long-input encoding for multi-document abstractive summarization,” Sci. Rep., vol. 15, p. 26529, 2025, doi: 10.1038/s41598-025-11062-2.

[33] M. W. Bagus, D. Satya, and A. Luthfiarta, “Leveraging BERT and T5 for Comprehensive Text Summarization on Indonesian Articles,” Jurnal Sistem Cerdas, vol. 8, no. 2, pp. 191–202, 2025, doi: 10.37396/jsc.v8i2.458.

[34] R. Dwi Putra, A. Rialdy Atmadja, and Y. A. Gerhana, “Improving Transformer Performance for Text Summarization in Video Transcription,” Journal of Computer Engineering, Electronics and Information Technology, vol. 4, no. 2, pp. 83–90, 2025, doi: 10.17509/coelite.v4i2.89353.

[35] Gitanjali Mishra, Nilambar Sethi, Agilandeeswari Loganathan, Yu-Hsiu Lin, and Yu-Chen Hu, “Attention Free BIGBIRD Transformer for Long Document Text Summarization”, IJCISIM, vol. 16, no. 2, p. 20, May 2024.

[36] H. Yuan and H. Zhang, “DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization,” in Findings of the Association for Computational Linguistics: NAACL 2025, Association for Computational Linguistics, Apr. 2025, pp. 2219–2231. doi: 10.18653/v1/2025.findings-naacl.118.

[37] E. Daraghmi, L. Atwe, and A. Jaber, “A Comparative Study of PEGASUS, BART, and T5 for Text Summarization Across Diverse Datasets,” Future Internet, vol. 17, no. 9, Sep. 2025, doi: 10.3390/fi17090389.

[38] Y. Huang, L. Sun, C. Han, and J. Guo, “A High-Precision Two-Stage Legal Judgment Summarization,” Mathematics, vol. 11, no. 6, p. 1320, 2023, doi: 10.3390/math11061320.

[39] D. Premasiri, T. Ranasinghe, R. Mitkov, M. El-Haj, and I. Frommholz, “Survey on legal information extraction: current status and open challenges,” Knowl. Inf. Syst., vol. 67, pp. 11287–11358, 2025, doi: 10.1007/s10115-025-02600-5.

[40] Mrunal Salwadkar, “Distributed Delivery Pipelines for Mobile and Ubiquitous Learning Platforms”, Secits Journal of Scalable Distributed Computing and Pipeline Automation, vol. 1, no. 1, pp. 39–47, Dec. 2024, Accessed: May 25, 2026. [Online]. Available: https://secitsociety.org/index.php/SJSDCPA/article/view/160

[41] A. Zhang, Z. C. Lipton, M. U. Li, and A. J. Smola, Dive into Deep Learning. Cambridge (atau New York/London sesuai imprint Cambridge): Cambridge University Press, 2024. Accessed: Feb. 02, 2026. [Online]. Available: https://www.cambridge.org/9781009389433

[42] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA: MIT Press, 2016. Accessed: Feb. 02, 2026. [Online]. Available: http://www.deeplearningbook.org

[43] S. Sharma, G. Aggarwal, and B. Kumar, “A survey on the dataset, techniques, and evaluation metric used for abstractive text summarization,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 22, no. 3, pp. 681–689, Jun. 2024, doi: 10.12928/TELKOMNIKA.v22i3.25512.

[44] N. Firdaus, B. Kusuma Riasti, and M. Asri Safi’ie, “Comparative Study Of Transformer-Based Models For Automated Resume Classification,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 11, no. 2, pp. 372–381, Nov. 2025, doi: 10.33480/jitk.v11i2.7453.

[45] A. Auriemma Citarella, M. Barbella, M. G. Ciobanu, F. De Marco, L. Di Biasi, and G. Tortora, “Assessing the effectiveness of ROUGE as unbiased metric in Extractive vs. Abstractive summarization techniques,” J. Comput. Sci., vol. 87, May 2025, doi: 10.1016/j.jocs.2025.102571.

[46] Junadhi, Agustin, L. Efrizoni, F. Okmayura, D. R. Habibie, and Muslim, “Improving Evaluation Metrics for Text Summarization: A Comparative Study and Proposal of a Novel Metric,” Journal of Applied Data Sciences, vol. 6, no. 2, pp. 885–896, May 2025, doi: 10.47738/jads.v6i2.547.

[47] T. Sadikot and S. Jain, “Legal Document Summarization: A Zero-shot Modular Agentic Workflow Approach,” in Proceedings of the 1st Workshop on NLP for Empowering Justice (JUST-NLP 2025), Association for Computational Linguistics, 2025, pp. 29–40. Accessed: Feb. 02, 2026. [Online]. Available: https://aclanthology.org/2025.justnlp-main.5/

Downloads

Published

2026-05-26

Issue

Vol. 11 No. 4 (2026): JITK Issue May 2026

Section

Articles

License

Copyright (c) 2026 Faradhita Eka Septiana, Febri Bagus Triwibowo, Galih Wasis Wicaksono

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

How to Cite

[1]
“ABSTRACTIVE SUMMARIZATION FOR INDONESIAN HUMAN TRAFFICKING COURT DECISIONS USING TRANSFORMER MODELS”, jitk, vol. 11, no. 4, pp. 1212–1223, May 2026, doi: 10.33480/jitk.v11i4.8221.