Long document summarization systems are critical for domains with lengthy and jargonladen text, yet they present significant challenges to researchers and developers with limited computing resources. Existing solutions mainly focus on efficient attentions or divide-and-conquer strategies. The former reduces theoretical time complexity, but is still memory-heavy. The latter methods sacrifice global context, leading to uninformative and incoherent summaries. This work aims to leverage the memory-efficient nature of divide-and-conquer methods while preserving global context. Concretely, our framework AWESOME uses two novel mechanisms: (1) External memory mechanisms track previously encoded document segments and their corresponding summaries, to enhance global document understanding and summary coherence. (2) Global salient content is further identified beforehand to augment each document segment to support its summarization. Extensive experiments on diverse genres of text, including government reports, transcripts, scientific papers, and novels, show that AWESOME produces summaries with improved informativeness, faithfulness, and coherence than competitive baselines on longer documents, while having a smaller GPU memory footprint.

翻译：长文档摘要系统对于处理术语密集的长篇文本领域至关重要，然而这些系统给计算资源有限的研究人员和开发者带来了重大挑战。现有解决方案主要聚焦于高效注意力机制或分治策略：前者虽降低了理论时间复杂度，但仍存在高内存消耗问题；后者则因牺牲全局上下文导致摘要信息量不足且缺乏连贯性。本研究旨在兼顾分治方法的内存高效性与全局上下文的完整性。具体而言，我们提出的AWESOME框架采用了两种创新机制：(1) 外部记忆机制通过追踪先前编码的文档片段及其对应摘要，增强全局文档理解与摘要连贯性；(2) 预先识别全局显著内容以增强每个文档片段，辅助其摘要生成。在涵盖政府报告、会议记录、科学论文及小说等多元文本类型上的大量实验表明，相较于竞争基线方法，AWESOME在处理长文档时能生成信息量更丰富、忠实度更高、连贯性更强的摘要，同时保持更小的GPU内存占用。