Ranking Sentences for Extractive Summarization with Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning approach to train neural models for extractive summarization by directly optimizing the ROUGE metric, leading to improved performance on benchmark datasets.

Contribution

It presents a novel reinforcement learning training algorithm that globally optimizes ROUGE for sentence ranking in extractive summarization, outperforming existing methods.

Findings

Outperforms state-of-the-art extractive and abstractive models

Demonstrates effectiveness on CNN and DailyMail datasets

Achieves higher ROUGE scores and better human evaluation

Abstract

Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. We use our algorithm to train a neural summarization model on the CNN and DailyMail datasets and demonstrate experimentally that it outperforms state-of-the-art extractive and abstractive systems when evaluated automatically and by humans.