Detail of the topics extracted from DUC2002.

Automatic Text Summarization (ATS) is gaining popularity as there is a growing demand for a system capable of processing extensive textual content and delivering a concise, yet meaningful, relevant, and useful summary. Manual summarization is both expensive and time-consuming, making it impractical for humans to handle vast amounts of data. Consequently, the need for ATS systems has become evident. These systems encounter challenges such as ensuring comprehensive content coverage, determining the appropriate length of the summary, addressing redundancy, and maintaining coherence in the generated summary. Researchers are actively addressing these challenges by employing Natural Language Processing (NLP) techniques. While traditional methods exist for generating summaries, they often fall short of addressing multiple aspects simultaneously. To overcome this limitation, recent advancements have introduced multi-objective evolutionary algorithms for ATS. This study proposes an enhancement to the performance of ATS through the utilization of an improved version of the Binary Multi-Objective Grey Wolf Optimizer (BMOGWO), incorporating mutation. The performance of this enhanced algorithm is assessed by comparing it with state-of-the-art algorithms using the DUC2002 dataset. Experimental results demonstrate that the proposed algorithm significantly outperforms the compared approaches.

自动文本摘要（Automatic Text Summarization, ATS）正日益受到关注，当前对于可处理海量文本内容、输出兼具简洁性与意义性、相关性及实用性的摘要的系统需求与日俱增。人工摘要不仅成本高昂且耗时漫长，人类难以独立处理海量数据，因此自动文本摘要系统的需求愈发凸显。这类系统面临诸多核心挑战：需确保内容覆盖全面、确定摘要的合适长度、处理冗余问题，以及维持生成摘要的连贯性。研究人员正积极借助自然语言处理（Natural Language Processing, NLP）技术应对这些挑战。传统的摘要生成方法往往无法同时兼顾多个优化维度。为突破这一局限，近期的研究进展已将多目标进化算法引入自动文本摘要任务。本研究提出一种性能优化方案，通过引入变异操作的二进制多目标灰狼优化器（Binary Multi-Objective Grey Wolf Optimizer, BMOGWO）的增强版本，提升自动文本摘要系统的性能。为评估该增强算法的表现，本研究以DUC2002数据集为基准，将其与当前主流算法开展对比实验。实验结果表明，所提算法的性能显著优于所对比的各类方法。