Saved in:
Bibliographic Details
Main Authors: Cho, Seonglae, Cho, Yonggi, Lee, HoonJae, Jang, Myungha, Yeo, Jinyoung, Lee, Dongha
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.13895
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911016742289408
author Cho, Seonglae
Cho, Yonggi
Lee, HoonJae
Jang, Myungha
Yeo, Jinyoung
Lee, Dongha
author_facet Cho, Seonglae
Cho, Yonggi
Lee, HoonJae
Jang, Myungha
Yeo, Jinyoung
Lee, Dongha
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13895
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization
Cho, Seonglae
Cho, Yonggi
Lee, HoonJae
Jang, Myungha
Yeo, Jinyoung
Lee, Dongha
Computation and Language
Machine Learning
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.
title RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2310.13895