Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization

TL;DR

This paper introduces a novel unsupervised extractive document summarization method that leverages graph centrality and centroid matching to select representative sentences at the summary level, outperforming existing methods.

Contribution

It proposes a graph-based approach that operates at the summary level using centrality and centroid, differing from traditional sentence ranking techniques.

Findings

Effective in selecting representative summaries

Outperforms state-of-the-art baselines

Validated on benchmark datasets

Abstract

Unsupervised document summarization has re-acquired lots of attention in recent years thanks to its simplicity and data independence. In this paper, we propose a graph-based unsupervised approach for extractive document summarization. Instead of ranking sentences by salience and extracting sentences one by one, our approach works at a summary-level by utilizing graph centrality and centroid. We first extract summary candidates as subgraphs based on centrality from the sentence graph and then select from the summary candidates by matching to the centroid. We perform extensive experiments on two bench-marked summarization datasets, and the results demonstrate the effectiveness of our model compared to state-of-the-art baselines.