Ranking Sentences for Extractive Summarization with Reinforcement Learning
This work addresses the problem of generating high-quality summaries for single documents, benefiting applications like news aggregation, though it is incremental as it builds on existing extractive and abstractive methods.
The authors tackled extractive summarization by framing it as a sentence ranking problem and introduced a reinforcement learning algorithm to optimize ROUGE scores, achieving state-of-the-art performance on CNN and DailyMail datasets in both automatic and human evaluations.
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.