Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning

TL;DR

This paper introduces RL-MMR, a reinforcement learning approach guided by Maximal Marginal Relevance, to improve multi-document summarization by reducing redundancy and enhancing neural representation learning, achieving state-of-the-art results.

Contribution

The paper proposes RL-MMR, integrating MMR guidance into neural reinforcement learning for MDS, addressing redundancy and training data limitations.

Findings

RL-MMR achieves state-of-the-art results on benchmark datasets.

Incorporating MMR improves learning efficiency and summary quality.

RL-MMR effectively reduces redundancy in multi-document summaries.

Abstract

While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS). We observe two major challenges when adapting SDS advances to MDS: (1) MDS involves larger search space and yet more limited training data, setting obstacles for neural methods to learn adequate representations; (2) MDS needs to resolve higher information redundancy among the source documents, which SDS methods are less effective to handle. To close the gap, we present RL-MMR, Maximal Margin Relevance-guided Reinforcement Learning for MDS, which unifies advanced neural SDS methods and statistical measures used in classical MDS. RL-MMR casts MMR guidance on fewer promising candidates, which restrains the search space and thus leads to better representation learning. Additionally, the explicit redundancy measure in MMR helps the neural representation of the summary to better capture redundancy. Extensive experiments demonstrate that RL-MMR achieves state-of-the-art performance on benchmark MDS datasets. In particular, we show the benefits of incorporating MMR into end-to-end learning when adapting SDS to MDS in terms of both learning effectiveness and efficiency.