论文标题
基于PCFG的自然语言界面改善了受控文本生成的概括
PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation
论文作者
论文摘要
对受控文本生成（CTG）的现有工作假定分类属性的控制接口。在这项工作中，我们提出了一种自然语言（NL）界面，在该界面中，我们制作一个PCFG将控制属性嵌入自然语言命令中，并提出了将命令作为输入的现有CTG模型的变体。在我们的实验中，我们设计了量身定制的设置以测试模型的概括能力。我们发现我们的基于PCFG的命令生成方法可有效地处理看不见的命令与FIX-SET模板相比。我们提出的NL模型可以有效地推广到看不见的属性，NL接口启用的新功能以及看不见的属性组合。有趣的是，我们发现，通过提出的NL接口增强的简单有条件生成方法在那些充满挑战的环境中是一个强大的基线。
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.
