A Question-Answering Based Framework/Metric for Evaluation of Newspaper Article Summarization

Vasanth Seemakurthy, Shashank Sundar, Siddharth Arvind, Siddhant Jagdish, Ashwini M. Joshi


Abstract
Condensed summaries of newspaper articles cater to the modern need for easily digestible content amid shrinking attention spans. However, current summarization systems often produce extracts failing to capture the essence of original articles. Traditional evaluation metrics like ROUGE also provide limited insights into whether key information is preserved in the summaries. To address this, we propose a pipeline to generate high-quality summaries tailored for newspaper articles and evaluate them using a question-answering based metric. Our system segments input newspaper images, extracts text, and generates summaries. We also generate relevant questions from the original articles and use a question-answering model to assess how well the summaries can answer these queries to evaluate summary quality beyond just lexical overlap. Experiments on real-world data show the potential effectiveness of our approach in contrast to conventional metrics. Our framework holds promise for enabling reliable news summary generation and evaluation systems.
Anthology ID:
2025.ranlp-1.125
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
1085–1089
Language:
URL:
https://aclanthology.org/2025.ranlp-1.125/
DOI:
Bibkey:
Cite (ACL):
Vasanth Seemakurthy, Shashank Sundar, Siddharth Arvind, Siddhant Jagdish, and Ashwini M. Joshi. 2025. A Question-Answering Based Framework/Metric for Evaluation of Newspaper Article Summarization. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1085–1089, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
A Question-Answering Based Framework/Metric for Evaluation of Newspaper Article Summarization (Seemakurthy et al., RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.125.pdf