arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.02794stat.MLcs.AIcs.LG
收藏

用于文本生成的令牌操纵生成对抗网络

Token Manipulation Generative Adversarial Network for Text Generation

DaeJin Jo

摘要:

MaskGAN通过填充给定标记之间的空白来打开条件语言模型的查询。在本文中,我们专注于解决必须指定要填充的空白所造成的限制。我们将条件文本生成问题分解为两个任务,使一个空白和填写空白,并扩展前者处理更复杂的操作给定的令牌。我们将这些任务作为一个分层的多代理RL问题,并引入了一个条件对抗学习,允许代理达到一个目标,在合作环境中产生现实的文本。我们表明,该模型不仅解决了局限性,但也提供了良好的结果,而不影响性能的质量和多样性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑