A New Sentence Extraction Strategy for Unsupervised Extractive Summarization Methods

TL;DR

This paper introduces a novel unsupervised sentence extraction strategy for extractive text summarization, leveraging Information Theory to improve feature distribution and reduce mutual information among sentences, showing effectiveness across datasets.

Contribution

The paper proposes a new sentence extraction strategy based on Information Theory, applicable to existing unsupervised methods, enhancing their performance without large datasets.

Findings

Strategy improves summarization quality

Effective across multiple datasets

Reduces mutual information among sentences

Abstract

In recent years, text summarization methods have attracted much attention again thanks to the researches on neural network models. Most of the current text summarization methods based on neural network models are supervised methods which need large-scale datasets. However, large-scale datasets are difficult to obtain in practical applications. In this paper, we model the task of extractive text summarization methods from the perspective of Information Theory, and then describe the unsupervised extractive methods with a uniform framework. To improve the feature distribution and to decrease the mutual information of summarization sentences, we propose a new sentence extraction strategy which can be applied to existing unsupervised extractive methods. Experiments are carried out on different datasets, and results show that our strategy is indeed effective and in line with expectations.