PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies
arXiv:2105.08244
Abstract
We propose a novel reinforcement learning based framework PoBRL for solving multi-document summarization. PoBRL jointly optimizes over the following three objectives necessary for a high-quality summary: importance, relevance, and length. Our strategy decouples this multi-objective optimization into different subproblems that can be solved individually by reinforcement learning. Utilizing PoBRL, we then blend each learned policies together to produce a summary that is a concise and complete representation of the original input. Our empirical analysis shows state-of-the-art performance on several multi-document datasets. Human evaluation also shows that our method produces high-quality output.
References in corpus (9)
- A Deep Reinforced Model for Abstractive Summarization
- An Actor-Critic Algorithm for Sequence Prediction
- Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting
- Yara Parser: A Fast and Accurate Dependency Parser
- Graph-based Neural Multi-Document Summarization
- Actor-Critic based Training Framework for Abstractive Summarization
- Improving Multi-Document Summarization via Text Classification
- Mix&Match - Agent Curricula for Reinforcement Learning
- BanditSum: Extractive Summarization as a Contextual Bandit