RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization
This work addresses interpretable summarization for users needing fine-grained insights, but it appears incremental as it builds on existing relation-based and language model approaches.
The authors tackled document summarization by proposing RTSUM, an unsupervised framework that uses relation triples as basic units, achieving results through multi-level salience scoring and a text-to-text language model, with a web demo for interpretability.
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 support for customization options, our tool visualizes the salience for textual units at three distinct levels: sentences, relation triples, and phrases. The codes,are publicly available.