PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation. (arXiv:2210.07431v1 [cs.CL])

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 …

arxiv controlled text generation language natural natural language text text generation