Warm-Starting for Improving the Novelty of Abstractive Summarization

Warm-Starting for Improving the Novelty of Abstractive Summarization

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 v...

Full description

Bibliographic Details
Main Authors: Ayham Alomari, Ahmad Sami Al-Shamayleh, Norisma Idris, Aznul Qalid Md Sabri, Izzat Alsmadi, Danah Omary
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Abstractive summarization
novelty
warm-started models
deep learning
metrics
Online Access:https://ieeexplore.ieee.org/document/10272590/

Internet

https://ieeexplore.ieee.org/document/10272590/

Similar Items