Multi-document Summarization by Ensembling of Scoring and Topic Modeling Techniques

Rajendra Kumar Roul, Navpreet, Saif Nalband


Abstract
With the growing volume of text, finding relevant information is increasingly difficult. Automatic Text Summarization (ATS) addresses this by efficiently extracting relevant content from large document collections. Despite progress, ATS faces challenges like managing long, repetitive sentences, preserving coherence, and maintaining semantic alignment. This work introduces an extractive summarization approach based on topic modeling to address these issues. The proposed method produces summaries with representative sentences, reduced redundancy, concise content, and strong semantic consistency. Its effectiveness, demonstrated through experiments on DUC datasets, outperforms state-of-the-art techniques.
Anthology ID:
2024.icon-1.69
Volume:
Proceedings of the 21st International Conference on Natural Language Processing (ICON)
Month:
December
Year:
2024
Address:
AU-KBC Research Centre, Chennai, India
Editors:
Sobha Lalitha Devi, Karunesh Arora
Venue:
ICON
SIG:
Publisher:
NLP Association of India (NLPAI)
Note:
Pages:
588–592
Language:
URL:
https://aclanthology.org/2024.icon-1.69/
DOI:
Bibkey:
Cite (ACL):
Rajendra Kumar Roul, Navpreet, and Saif Nalband. 2024. Multi-document Summarization by Ensembling of Scoring and Topic Modeling Techniques. In Proceedings of the 21st International Conference on Natural Language Processing (ICON), pages 588–592, AU-KBC Research Centre, Chennai, India. NLP Association of India (NLPAI).
Cite (Informal):
Multi-document Summarization by Ensembling of Scoring and Topic Modeling Techniques (Roul et al., ICON 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.icon-1.69.pdf