Robust Deep Reinforcement Learning for Extractive Legal Summarization
This work addresses the challenge of summarizing complex legal documents, which is incremental as it applies existing RL methods to a specific domain.
The paper tackled the problem of automatic summarization of legal texts by using reinforcement learning to train deep summarization models, resulting in consistent and significant performance gains across three public legal datasets.
Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles. Recent advances of deep models trained end-to-end with differentiable losses can well-summarize natural text, yet when applied to legal domain, they show limited results. In this paper, we propose to use reinforcement learning to train current deep summarization models to improve their performance on the legal domain. To this end, we adopt proximal policy optimization methods and introduce novel reward functions that encourage the generation of candidate summaries satisfying both lexical and semantic criteria. We apply our method to training different summarization backbones and observe a consistent and significant performance gain across 3 public legal datasets.