Tools
Tools
Rezaei, H, Moeinzadeh Mirhosseini, SA, Shahgholian, A and Saraee, M (2024) Features in extractive supervised single-document summarization: case of Persian news. Language Resources and Evaluation. ISSN 1574-020X
|
Text
s10579-024-09739-7.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
Text summarization has been one of the most challenging areas of research in NLP. Much effort has been made to overcome this challenge by using either abstractive or extractive methods. Extractive methods are preferable due to their simplicity compared with the more elaborate abstractive methods. In extractive supervised single document approaches, the system will not generate sentences. Instead, via supervised learning, it learns how to score sentences within the document based on some textual features and subsequently selects those with the highest rank. Therefore, the core objective is ranking, which enormously depends on the document structure and context. These dependencies have been unnoticed by many state-of-the-art solutions. In this work, document-related features such as topic and relative length are integrated into the vectors of every sentence to enhance the quality of summaries.
Our experiment results show that the system takes contextual and structural patterns into account, which will increase the precision of the learned model. Consequently, our method will produce more comprehensive and concise summaries.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Supervised extractive summarization; Machine learning; Regression; Feature extraction; Natural language processing |
| Subjects: | H Social Sciences > HF Commerce > HF5001 Business Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) |
| Divisions: | Business & Management (from Sep 19) |
| Publisher: | Springer |
| SWORD Depositor: | A Symplectic |
| Date Deposited: | 09 May 2024 10:57 |
| Last Modified: | 09 May 2024 10:57 |
| DOI or ID number: | 10.1007/s10579-024-09739-7 |
| URI: | https://researchonline.ljmu.ac.uk/id/eprint/23216 |
 |
View Item |