Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization

TL;DR

This paper introduces an unsupervised, reinforcement learning-based abstractive summarization model that generates multiple summaries of varying lengths, outperforming existing extractive and abstractive methods.

Contribution

It proposes a novel reinforcement learning framework for unsupervised abstractive summarization that produces multiple summaries with different lengths, enhancing summary quality.

Findings

Outperforms existing models in summary quality

Generates summaries with many new words not in the input

Produces multiple summaries of varying lengths

Abstract

Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without human-written summaries. However, recent unsupervised models are extractive, which remove words from texts and thus they are less flexible than abstractive summarization. In this work, we devise an abstractive model based on reinforcement learning without ground-truth summaries. We formulate the unsupervised summarization based on the Markov decision process with rewards representing the summary quality. To further enhance the summary quality, we develop a multi-summary learning mechanism that generates multiple summaries with varying lengths for a given text, while making the summaries mutually enhance each other. Experimental results show that the proposed model substantially outperforms both abstractive and extractive models, yet frequently generating new words not contained in input texts.