We present a novel approach to generating scripts by using agents with different personality types. To manage character interaction in the script, we employ simulated dramatic networks. Automatic and human evaluation on multiple criteria shows that our approach outperforms a vanilla-GPT2-based baseline. We further introduce a new metric to evaluate dialogue consistency based on natural language inference and demonstrate its validity.

翻译：我们提出了一种新颖的方法,通过使用具有不同个性类型的代理人来生成脚本。为了管理脚本中的字符互动,我们使用了模拟戏剧网络。对多种标准的自动和人性评估表明,我们的方法优于香草-GPT2基基线。我们进一步引入了一种新的衡量标准,以评估基于自然语言推论的对话一致性并展示其有效性。