Alomari, Ayham and Al-Shamayleh, Ahmad Sami and Idris, Norisma and Qalid Md Sabri, Aznul and Alsmadi, Izzat and Omary, Danah (2023) Warm-Starting for Improving the Novelty of Abstractive Summarization. IEEE Access, 11. pp. 112483-112501. ISSN 2169-3536, DOI https://doi.org/10.1109/ACCESS.2023.3322226.
Full text not available from this repository.Abstract
The Abstractive summarization is distinguished by using novel phrases that are not found in the source text. However, most previous research ignores this feature in favour of enhancing syntactical similarity with the reference. To improve novelty aspects, we have used multiple warm-started models with varying encoder and decoder checkpoints and vocabulary. These models are then adapted to the paraphrasing task and the sampling decoding strategy to further boost the levels of novelty and quality. In addition, to avoid relying only on the syntactical similarity assessment, two additional abstractive summarization metrics are introduced: 1) NovScore: a new novelty metric that delivers a summary novelty score; and 2) NSSF: a new comprehensive metric that ensembles Novelty, Syntactic, Semantic, and Faithfulness features into a single score to simulate human assessment in providing a reliable evaluation. Finally, we compare our models to the state-of-the-art sequence-to-sequence models using the current and the proposed metrics. As a result, warm-starting, sampling, and paraphrasing improve novelty degrees by 2%, 5%, and 14%, respectively, while maintaining comparable scores on other metrics.
| Item Type: | Article |
|---|---|
| Funders: | Ministry of Education, Malaysia (JPT(BKPI)1000/016/018/25(58)) |
| Uncontrolled Keywords: | Abstractive summarization; novelty; warm-started models; deep learning; metrics |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Computer Science & Information Technology > Department of Artificial Intelligence |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 17 Jul 2025 03:33 |
| Last Modified: | 17 Jul 2025 03:33 |
| URI: | http://eprints.um.edu.my/id/eprint/50947 |
Actions (login required)
 |
View Item |
