An unsupervised extractive summarization method based on multi-round computation

Abstract

Text summarization methods have attracted much attention all the time. In recent years, deep learning has been applied to text summarization, and it turned out to be pretty effective. However, most of the current text summarization methods based on deep learning need largescale datasets, which is difficult to achieve in practical applications. In this paper, an unsupervised extractive text summarization method based on multi-round calculation is proposed. Based on the directed graph algorithm, we change the traditional method of calculating the sentence ranking at one time to multi-round calculation, and the summary sentences are dynamically optimized after each round of calculation to better match the characteristics of the text. In this paper, experiments are carried out on four data sets, each separately containing Chinese, English, long and short texts. The experiment results show that our method has better performance than both baseline methods and other unsupervised methods and is robust on different datasets.

Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions

“…We propose a novel reweighting approach that can tackle this problem. A prior attempt (Tao et al, 2021) on multi-round selection looked at the local similarity between selected sentences. They iteratively recompute the sentence to sentence similarities between the selected summary sentences and recompute the final sentence centrality scores after each sentence selection.…”