How Good are LM and LLMs in Bangla Newspaper Article Summarization?

Keywords

CCDS Authors

MD Fahim

MD Fahim

• Research Assistant, CCDS

Research Interests

Machine Learning, Natural Language Processing

Meheraj Hossain

Meheraj Hossain

• Research Assistant, CCDS

Machine Learning Engineer II

Therap (BD) Ltd

Research Interests

Machine Learning

M Ashraful Amin, PhD

M Ashraful Amin, PhD

• Founder Director, CCDS
• Director, AI/ML, HCI & DS Wings

Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

Amin Ahsan Ali, PhD

Amin Ahsan Ali, PhD

• Director, AI/ML Wing

Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Research Interests

Artificial Intelligence, Machine Learning

References

1. 1.Wafaa S. El-Kassas, Cherif Salama, Ahmed Rafea, Hoda K. Mohamed. (2020). Automatic text summarization: A comprehensive survey. Expert Systems with Applications, 165, 113679[10.1016/j.eswa.2020.113679]
2. 2.Shengli Song, Haitao Huang, Tongxiao Ruan. (2018). Abstractive text summarization using LSTM-CNN based deep learning. Multimedia Tools and Applications, 78(1), 857–875[10.1007/s11042-018-5749-3]
3. 3.Adhika Pramita Widyassari, Supriadi Rustad, Guruh Fajar Shidik, Edi Noersasongko, Abdul Syukur, Affandy Affandy, De Rosal Ignatius Moses Setiadi. (2020). Review of automatic text summarization techniques & methods. Journal of King Saud University - Computer and Information Sciences, 34(4), 1029–1046[10.1016/j.jksuci.2020.05.006]
4. 4.Tahmid Hasan, Abhik Bhattacharjee, Md. Saiful Islam, Kazi Mubasshir, Yuan-Fang Li, Yong‐Bin Kang, M. Sohel Rahman, Rifat Shahriyar. (2021). XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages. , 4693–4703[10.18653/v1/2021.findings-acl.413]
5. 5.Tian Shi, Yaser Keneshloo, Naren Ramakrishnan, Chandan K. Reddy. (2021). Neural Abstractive Text Summarization with Sequence-to-Sequence Models. ACM/IMS Transactions on Data Science, 2(1), 1–37[10.1145/3419106]
6. 6.Jonathan Pilault, Raymond Li, Sandeep Subramanian, Chris Pal. (2020). On Extractive and Abstractive Neural Document Summarization with Transformer Language Models. , 9308–9319[10.18653/v1/2020.emnlp-main.748]
7. 7.Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Kazi Samin Mubasshir, Md. Saiful Islam, Anindya Iqbal, M. Sohel Rahman, Rifat Shahriyar. (2022). BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla. Findings of the Association for Computational Linguistics: NAACL 2022, 1318–1327[10.18653/v1/2022.findings-naacl.98]
8. 8.Rasim Alguliyev, Ramiz M. Aliguliyev, Nijat R. Isazade, Asad Abdi, Norisma Idris. (2018). COSUM: Text summarization based on clustering and optimization. Expert Systems, 36(1)[10.1111/exsy.12340]
9. 9.Ayesha Ayub Syed, Ford Lumban Gaol, Tokuro Matsuo. (2021). A Survey of the State-of-the-Art Models in Neural Abstractive Text Summarization. IEEE Access, 9, 13248–13265[10.1109/access.2021.3052783]
10. 10.Betül Ay, Fatih Ertam, Guven Fidan, Galip Aydın. (2023). Turkish abstractive text document summarization using text to text transfer transformer. Alexandria Engineering Journal, 68, 1–13[10.1016/j.aej.2023.01.008]
11. 11.Akash Ghosh, A. Seetharama Acharya, Raghav Jain, Sriparna Saha, Aman Chadha, Setu Sinha. (2024). CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare. Proceedings of the AAAI Conference on Artificial Intelligence, 38(20), 22031–22039[10.1609/aaai.v38i20.30206]
12. 12.Md. Motiur Rahman, Fazlul Hasan Siddiqui. (2019). An Optimized Abstractive Text Summarization Model Using Peephole Convolutional LSTM. Symmetry, 11(10), 1290[10.3390/sym11101290]
13. 13.Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Rifat Shahriyar. (2023). BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla. , 726–735[10.18653/v1/2023.findings-eacl.54]
14. 14.Partha Protim Ghosh, Rezvi Shahariar, Muhammad Asif Khan. (2018). A Rule Based Extractive Text Summarization Technique for Bangla News Documents. International Journal of Modern Education and Computer Science, 10(12), 44–53[10.5815/ijmecs.2018.12.06]
15. 15.Batuhan Baykara, Tunga Güngör. (2022). Turkish abstractive text summarization using pretrained sequence-to-sequence models. Natural Language Engineering, 29(5), 1275–1304[10.1017/s1351324922000195]
16. 16.Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Yuan-Fang Li, Yong‐Bin Kang, Rifat Shahriyar. (2023). CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs. , 2541–2564[10.18653/v1/2023.acl-long.143]
17. 17.Xuefeng Xi, Zhou Pi, Guodong Zhou. (2020). Global Encoding for Long Chinese Text Summarization. ACM Transactions on Asian and Low-Resource Language Information Processing, 19(6), 1–17[10.1145/3407911]
18. 18.Youhyun Shin. (2023). Multi-Encoder Transformer for Korean Abstractive Text Summarization. IEEE Access, 11, 48768–48782[10.1109/access.2023.3277754]
19. 19.Noureen Fatima, Sher Muhammad Daudpota, Zenun Kastrati, Ali Shariq Imran, Saif Hassan, Nouh Sabri Elmitwally. (2023). Improving news headline text generation quality through frequent POS-Tag patterns analysis. Engineering Applications of Artificial Intelligence, 125, 106718[10.1016/j.engappai.2023.106718]
20. 20.Aman Kumar, Himani Shrotriya, Prachi Sahu, Amogh Mishra, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan, Mitesh M. Khapra, Pratyush Kumar. (2022). IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages. , 5363–5394[10.18653/v1/2022.emnlp-main.360]
21. 21.Padhma Muniraj, K.R. Sabarmathi, R. Leelavathi, Saravana Balaji B. (2023). HNTSumm: Hybrid text summarization of transliterated news articles. International Journal of Intelligent Networks, 4, 53–61[10.1016/j.ijin.2023.03.001]
22. 22.Zijian Ding, Alison Smith, Wenjuan Zhang, Joel Tetreault, Alejandro Jaimes. (2023). Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation. , 3321–3339[10.18653/v1/2023.findings-emnlp.217]
23. 23.Waseemullah Waseemullah, Zainab Fatima, Shehnila Zardari, Muhammad Fahim, Maria Andleeb Siddiqui, Ag Asri Ag Ibrahim, Kashif Nisar, Laviza Falak Naz. (2022). A Novel Approach for Semantic Extractive Text Summarization. Applied Sciences, 12(9), 4479[10.3390/app12094479]
24. 24.Alvi Khan, Fida Kamal, Mohammad Abrar Chowdhury, Tasnim Ahmed, Md Tahmid Rahman Laskar, Sabbir Ahmed. (2023). BanglaCHQ-Summ: An Abstractive Summarization Dataset for Medical Queries in Bangla Conversational Speech. , 85–93[10.18653/v1/2023.banglalp-1.10]
25. 25.Tahmid Hasan, Abhik Bhattacharjee, Kazi Samin, Masum Hasan, Madhusudan Basak, M. Sohel Rahman, Rifat Shahriyar. (2020). Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation. , 2612–2623[10.18653/v1/2020.emnlp-main.207]
26. 26.M. Esther Hannah. (2019). A hybrid classification-based model for automatic text summarisation using machine learning approaches: CBS-ID3MV. International Journal of Product Development, 23(2/3), 201[10.1504/ijpd.2019.099242]
27. 27.Colin Raffel, Noam Shazeer, Adam P. Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. (2019). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv (Cornell University), 21(140), 1–67[10.48550/arxiv.1910.10683]

Cited By

1. 1.Washik Wali Faieaz, Sayma Jannat, Pronoy Kumar Mondal, Sadman Sadik Khan, Shuvo Karmaker, Md Sadekur Rahman. (2025). Advancing Bangla NLP: Transformer-Based Question Generation using Fine-Tuned LLM. , 1–7[10.1109/ecce64574.2025.11013206]
2. 2.Prerana Khatiwada, Varun Pappu, Benjamin E. Bagozzi, Matthew Louis Mauriello. (2026). When AI Rewrites the News: How Sentiment, Framing, and LLM Disclosure Shape Perceptions. , 1–25[10.1145/3772318.3791527]
3. 3.Md Saiyem Raiyan, Nayeema Ferdous. (2025). SumLLM: Performance Evaluation and the Judgment of Large Language Models in Bengali Abstractive News Summarization. , 5584–5589[10.1109/iccit68739.2025.11491391]