@Article{iasc.2023.034718,
AUTHOR = {Ibrahim M. Alwayle, Hala J. Alshahrani, Saud S. Alotaibi, Khaled M. Alalayah, Amira Sayed A. Aziz, Khadija M. Alaidarous, Ibrahim Abdulrab Ahmed, Manar Ahmed Hamza},
TITLE = {Abstractive Arabic Text Summarization Using Hyperparameter Tuned Denoising Deep Neural Network},
JOURNAL = {Intelligent Automation \& Soft Computing},
VOLUME = {38},
YEAR = {2023},
NUMBER = {2},
PAGES = {153--168},
URL = {http://www.techscience.com/iasc/v38n2/55469},
ISSN = {2326-005X},
ABSTRACT = {Abstractive text summarization is crucial to produce summaries of natural language with basic concepts from large text documents. Despite the achievement of English language-related abstractive text summarization models, the models that support Arabic language text summarization are fewer in number. Recent abstractive Arabic summarization models encounter different issues that need to be resolved. Syntax inconsistency is a crucial issue resulting in the low-accuracy summary. A new technique has achieved remarkable outcomes by adding topic awareness in the text summarization process that guides the module by imitating human awareness. The current research article presents Abstractive Arabic Text Summarization using Hyperparameter Tuned Denoising Deep Neural Network (AATS-HTDDNN) technique. The presented AATS-HTDDNN technique aims to generate summaries of Arabic text. In the presented AATS-HTDDNN technique, the DDNN model is utilized to generate the summary. This study exploits the Chameleon Swarm Optimization (CSO) algorithm to fine-tune the hyperparameters relevant to the DDNN model since it considerably affects the summarization efficiency. This phase shows the novelty of the current study. To validate the enhanced summarization performance of the proposed AATS-HTDDNN model, a comprehensive experimental analysis was conducted. The comparison study outcomes confirmed the better performance of the AATS-HTDDNN model over other approaches.},
DOI = {10.32604/iasc.2023.034718}
}