For text summarization, the role of discourse structure is pivotal in discerning the core content of a text. Regrettably, prior studies on incorporating Rhetorical Structure Theory (RST) into transformer-based summarization models only consider the nuclearity annotation, thereby overlooking the variety of discourse relation types. This paper introduces the 'RSTformer', a novel summarization model that comprehensively incorporates both the types and uncertainty of rhetorical relations. Our RST-attention mechanism, rooted in document-level rhetorical structure, is an extension of the recently devised Longformer framework. Through rigorous evaluation, the model proposed herein exhibits significant superiority over state-of-the-art models, as evidenced by its notable performance on several automatic metrics and human evaluation.

翻译：对于文本摘要而言，语篇结构在识别文本核心内容中起着关键作用。遗憾的是，先前将修辞结构理论（RST）融入基于Transformer的摘要模型的研究，仅考虑了核心性标注，从而忽略了语篇关系类型的多样性。本文提出"RSTformer"，一种新型摘要模型，全面融入了修辞关系的类型及其不确定性。我们的RST注意力机制根植于文档级修辞结构，是对近期提出的Longformer框架的延伸。通过严格评估，本文所提出的模型在多项自动评估指标和人工评估中均展现出显著优于当前最先进模型的性能。