Unsupervised methods are promising for abstractive text summarization in that the parallel corpora is not required. However, their performance is still far from being satisfied, therefore research on promising solutions is on-going. In this paper, we propose a new approach based on Q-learning with an edit-based summarization. The method combines two key modules to form an Editorial Agent and Language Model converter (EALM). The agent predicts edit actions (e.t., delete, keep, and replace), and then the LM converter deterministically generates a summary on the basis of the action signals. Q-learning is leveraged to train the agent to produce proper edit actions. Experimental results show that EALM delivered competitive performance compared with the previous encoder-decoder-based methods, even with truly zero paired data (i.e., no validation set). Defining the task as Q-learning enables us not only to develop a competitive method but also to make the latest techniques in reinforcement learning available for unsupervised summarization. We also conduct qualitative analysis, providing insights into future study on unsupervised summarizers.

翻译：不受监督的方法对抽象文本进行抽象文本总结很有希望,因为不需要平行的子公司。 但是,它们的性能还远远没有满足, 因此关于有希望的解决方案的研究正在进行中。 在本文中, 我们提出基于Q- 学习的新方法, 并使用基于编辑的汇总。 这个方法将两个关键模块合并成编辑代理和语言模型转换器( ELM) 。 代理商预测编辑行动( e.t., 删除、 保存和替换), 然后LM 转换器根据行动信号生成一个摘要。 Q- 学习被利用来培训代理商来产生适当的编辑行动。 实验结果显示, EALM 提供了与先前的编码- 解码器为基础的方法相比的竞争性业绩, 即使数据是真正零对齐的( 即没有验证集 ) 。 将任务定义为 Q- 不仅可以开发一种竞争性的方法, 还可以提供最新的技术, 强化学习, 以便不被监督的总结。 我们还进行定性分析, 向未来关于未监督的缩图师的研究提供洞察。