论文标题
代币操纵生成的对抗网络，用于文本生成
Token Manipulation Generative Adversarial Network for Text Generation
论文作者
论文摘要
Maskgan通过填充给定令牌之间的空白来打开有关条件语言模型的查询。在本文中，我们专注于解决必须填写空白而造成的限制。我们将有条件的文本生成问题分解为两个任务，即使是空白的和填充的任务，并扩展了前者以处理给定令牌上更复杂的操作。我们将这些任务视为分层多代理RL问题，并引入有条件的对抗性学习，该学习使代理人可以在合作环境中实现目标，产生现实的文本。我们表明，所提出的模型不仅解决了局限性，而且还提供了良好的结果，而不会在质量和多样性方面损害绩效。
MaskGAN opens the query for the conditional language model by filling in the blanks between the given tokens. In this paper, we focus on addressing the limitations caused by having to specify blanks to be filled. We decompose conditional text generation problem into two tasks, make-a-blank and fill-in-the-blank, and extend the former to handle more complex manipulations on the given tokens. We cast these tasks as a hierarchical multi agent RL problem and introduce a conditional adversarial learning that allows the agents to reach a goal, producing realistic texts, in cooperative setting. We show that the proposed model not only addresses the limitations but also provides good results without compromising the performance in terms of quality and diversity.
