一种新型的基于大语言模型的长对话两阶段摘要生成方法
A Novel LLM-based Two-stage Summarization Approach for Long Dialogues
AI总结：
针对长文档长度超出主流预训练语言模型输入容量的问题，提出含无监督主题分段、ChatGPT(v3.5)浓缩、生成式摘要微调的分层两阶段框架，可在资源受限场景下高效处理长文档摘要任务。
摘要：
长文档摘要生成是自然语言处理领域的一项重大挑战，原因在于输入文本的长度超出了多数当前最优预训练语言模型的处理容量。本研究提出一种分层框架，先对长文档的信息进行分段与浓缩，随后使用生成式摘要模型对处理后的文本进行微调。无监督主题分割方法用于识别语义上合理的分段断点；浓缩阶段采用无监督生成模型生成浓缩数据，当前实验使用的是ChatGPT(v3.5)；摘要生成阶段则在浓缩数据上微调生成式摘要模型，以生成最终结果。该框架即便在文档长度超出模型最大输入尺寸时，也能让模型完成长文档处理。由于摘要模型无需处理完整文档，训练所需的时间与计算资源得以减少，因此该框架适用于本地计算资源受限的场景。
英文摘要：
Long document summarization poses a significant challenge in natural language processing due to input lengths that exceed the capacity of most state-of-the-art pre-trained language models. This study proposes a hierarchical framework that segments and condenses information from long documents, subsequently fine-tuning the processed text with an abstractive summarization model. Unsupervised topic segmentation methods identify semantically appropriate breakpoints. The condensation stage utilizes an unsupervised generation model to generate condensed data, and our current experiments employ ChatGPT(v3.5). The summarization stage fine-tunes the abstractive summarization model on the condensed data to generate the final results. This framework enables long documents to be processed on models even when the document length exceeds the model's maximum input size. The exclusion of the entire document from the summarization model reduces the time and computational resources required for training, making the framework suitable for contexts with constrained local computational resources.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
