查看文章

In 2020, Sanchez-Gomez et al.[1] suggested a multi-objective artificial bee colony algorithm based on decomposition (MOABC/D) as a solution to the integrative multi-document text summarization issue. To make use of multi-core systems, the MOABC/D method had an asynchronous similar design built. Document understanding conference (DUC) datasets were used for the experiments, and ROUGE measures were used to assess the outcomes. The acquired results enhanced the ROUGE-1, ROUGE-2, and ROUGE-L scores reported in the scholarly literature while also indicating a very good speedup.

In 2021, Mojrian et al.[15] proposed a multi-document text summarization system using the quantum-inspired genetic algorithm (MTSQIGA) method, a revolutionary technique to multi-document text summarization that draws out key lines from a variety of source documents to produce the summary. To find the optimum solution, the recommended generic summarizer employs a modified quantum-inspired genetic algorithm (QIGA) to offer extractive summarization as a binary optimization. This approach’s objective function was crucial in maximizing the six phrase scoring measures that were composed of a concatenation of criteria for coverage, relevancy, and repetition. The recommended QIGA employs a self-adaptive quantum rotation gate along with a tailored quantum measurement, based on the grade and size of the summary, to ensure the development of a summary within a defined length limit. On benchmark datasets from DUC 2005 and 2007, the suggested scheme was assessed using ROUGE standard metrics. It also shows the potential …