PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation

arxiv(2022)

引用 0|浏览33
暂无评分
摘要
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.
更多
查看译文
关键词
controlled text generation,natural language interface,generalization,pcfg-based
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要