OTExtSum: Extractive Text Summarisation with Optimal Transport

TL;DR

OTExtSum introduces a novel non-learning-based extractive summarisation method using optimal transport theory, specifically Wasserstein distance, to select sentences that best cover the document's semantics, outperforming existing methods.

Contribution

This paper formulates extractive summarisation as an optimal transport problem, providing a new, interpretable, and effective non-learning-based approach that surpasses state-of-the-art methods.

Findings

Outperforms existing non-learning-based methods on multiple datasets

Achieves superior ROUGE scores compared to recent learning-based methods

Demonstrates the effectiveness of optimal transport in capturing semantic coverage

Abstract

Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary. While learning-based methods have achieved promising results, they have several limitations, such as dependence on expensive training and lack of interpretability. Therefore, in this paper, we propose a novel non-learning-based method by for the first time formulating text summarisation as an Optimal Transport (OT) problem, namely Optimal Transport Extractive Summariser (OTExtSum). Optimal sentence extraction is conceptualised as obtaining an optimal summary that minimises the transportation cost to a given document regarding their semantic distributions. Such a cost is defined by the Wasserstein distance and used to measure the summary's semantic coverage of the original document. Comprehensive experiments on four challenging and widely used datasets - MultiNews, PubMed, BillSum, and CNN/DM demonstrate that our proposed method outperforms the state-of-the-art non-learning-based methods and several recent learning-based methods in terms of the ROUGE metric.