AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content
This work addresses a practical challenge for researchers and developers with limited computing resources in domains like government reports and scientific papers, offering an incremental improvement over existing methods.
The paper tackles the problem of long document summarization under GPU memory constraints by introducing AWESOME, a framework that combines memory mechanisms and global salient content to preserve context while reducing memory usage, resulting in improved informativeness, faithfulness, and coherence compared to baselines.
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.