Existing work on controlled text generation (CTG) assumes a control interface of categorical attributes. In this work, we propose a natural language (NL) interface, where we craft a PCFG to embed the control attributes into natural language commands, and propose variants of existing CTG models that take commands as input. In our experiments, we design tailored setups to test model's generalization abilities. We find our PCFG-based command generation approach is effective for handling unseen commands compared to fix-set templates; our proposed NL models can effectively generalize to unseen attributes, a new ability enabled by the NL interface, as well as unseen attribute combinations. Interestingly, we discover that the simple conditional generation approach, enhanced with our proposed NL interface, is a strong baseline in those challenging settings.
翻译:在这项工作中,我们提出了一个自然语言界面(NL ), 用来将控制属性嵌入自然语言命令中,并提出了将控制属性嵌入自然语言命令的现有CTG模型的变体。在实验中,我们设计了专门设计的设置,以测试模型的通用能力。我们发现基于 PCFG 的指令生成方法对于处理无法见的命令与固定模板相比是有效的;我们提议的NL 模型可以有效地概括为不可见的属性、由NL 界面促成的新能力以及未知属性组合。 有趣的是,我们发现简单的有条件的生成方法,与我们提议的NL 界面相强化,是这些具有挑战性的环境中的坚实基准。