A Comprehensive Text Optimization Approach to Bangla Summarization

Irtifa Haider, Shanjida Alam


Abstract
The task of Bengali text optimization demands not only the generation of concise and coherent summaries but also grammatical accuracy, semantic appropriateness, and factual reliability. This study presents a dual-phase optimization framework for Bengali text summarization that integrates entity-preserving preprocessing and abstractive generation with mT5, followed by refinement through sentence ranking, entity consistency enforcement, and optimization with instruction-tuned LLMs such as mBART. Evaluations using ROUGE, BLEU,BERTScore, and human ratings of fluency, adequacy, coherence, and readability show consistent gains over baseline summarizers. By embedding grammatical and factual safe guards into the summarization pipeline, this study establishes a robust and scalable benchmark for Bengali NLP, advancing text optimization research. Our model achieves 0.54 ROUGE-1 and 0.88 BERTScore on BANSData, outperforming recent multilingual baselines.
Anthology ID:
2025.banglalp-1.13
Volume:
Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
Month:
December
Year:
2025
Address:
Mumbai, India
Editors:
Firoj Alam, Sudipta Kar, Shammur Absar Chowdhury, Naeemul Hassan, Enamul Hoque Prince, Mohiuddin Tasnim, Md Rashad Al Hasan Rony, Md Tahmid Rahman Rahman
Venues:
BanglaLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
151–160
Language:
URL:
https://aclanthology.org/2025.banglalp-1.13/
DOI:
Bibkey:
Cite (ACL):
Irtifa Haider and Shanjida Alam. 2025. A Comprehensive Text Optimization Approach to Bangla Summarization. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 151–160, Mumbai, India. Association for Computational Linguistics.
Cite (Informal):
A Comprehensive Text Optimization Approach to Bangla Summarization (Haider & Alam, BanglaLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.banglalp-1.13.pdf