RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization

arXiv:2310.13895v2 Announce Type: replace-cross
Abstract: In this paper, we present RTSUM, an unsupervised summarization framework that utilizes relation triples as the basic unit for summarization. Given an input document, RTSUM first selects salient relation triples via multi-level salience scoring and then generates a concise summary from the selected relation triples by using a text-to-text language model. On the basis of RTSUM, we also develop a web demo for an interpretable summarizing tool, providing fine-grained interpretations with the output summary. With …

abstract arxiv basic cs.cl cs.lg document framework paper scoring summarization summary type unsupervised via visualization