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.

翻译：法律文本的自动总结是一项重要任务,而且仍是一项艰巨的任务,因为法律文件往往冗长而复杂,具有不寻常的结构和风格。最近经过培训的深层次模型的近况,最终到最终,损失程度各异,可以很好地概括自然文本,但在应用到法律领域时,这些文本显示出有限的结果。在本文件中,我们提议利用强化学习来培训当前的深度总结模型,以提高其在法律领域的绩效。为此,我们采用了近似的政策优化方法,并引入新的奖励功能,鼓励生成符合法律标准和语义标准的候选摘要。我们运用我们的方法培训不同的总结骨干,并观察到在三个公共法律数据集中取得一致和显著的业绩收益。