Advancing automatic text summarization: Unleashing enhanced binary multi-objective grey wolf optimization with...

Area of Science:

• Computer Science
• Artificial Intelligence
• Natural Language Processing

Background:

• Automatic Text Summarization (ATS) is crucial for handling vast amounts of data, as manual summarization is time-consuming and expensive.
• Existing ATS systems face challenges in content coverage, summary length, redundancy, and coherence.
• Natural Language Processing (NLP) techniques are employed, but traditional methods struggle with multi-faceted optimization.

Purpose of the Study:

• To enhance the performance of Automatic Text Summarization (ATS).
• To introduce an improved Binary Multi-Objective Grey Wolf Optimizer (BMOGWO) with mutation for ATS.

Main Methods:

• Utilizing an enhanced Binary Multi-Objective Grey Wolf Optimizer (BMOGWO) incorporating mutation.
• Evaluating the proposed algorithm's performance against state-of-the-art methods.
• Testing on the DUC2002 dataset for comprehensive assessment.

Main Results:

• The enhanced BMOGWO algorithm demonstrates superior performance in ATS.
• Significant improvements were observed compared to existing state-of-the-art algorithms.
• The proposed method effectively addresses multiple summarization challenges simultaneously.

Conclusions:

• The enhanced BMOGWO algorithm represents a significant advancement in Automatic Text Summarization.
• This approach offers a more effective solution for generating high-quality, concise summaries.
• Further research can explore applications of this enhanced algorithm in various NLP tasks.