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.
@article{arxiv.2105.08244,
title = {PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies},
author = {Andy Su and Difei Su and John M. Mulvey and H. Vincent Poor},
journal= {arXiv preprint arXiv:2105.08244},
year = {2021}
}