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

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.

arXiv commentWe found some error in Table 2. We need some time to update the paper

References in corpus (14)

• Subgraph Centrality in Complex Networks
• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• Text Summarization with Pretrained Encoders
• Neural Summarization by Extracting Sentences and Words
• Get To The Point: Summarization with Pointer-Generator Networks
• Graph-based Neural Multi-Document Summarization
• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints
• Sentence Centrality Revisited for Unsupervised Summarization
• Discourse-Aware Neural Extractive Text Summarization
• Extractive Summarization as Text Matching
• Neural Document Summarization by Jointly Learning to Score and Select Sentences
• Summary Level Training of Sentence Rewriting for Abstractive Summarization
• A Closer Look at Data Bias in Neural Extractive Summarization Models