Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation. (arXiv:2204.13362v1 [cs.CL])

Attribute-based Controlled Text Generation (CTG) refers to generating
sentences that satisfy desirable attributes (e.g., emotions and topics).
Existing works often utilize fine-tuning or resort to extra attribute
classifiers, yet suffer from storage and inference time increases. To address
these concerns, we explore attribute-based CTG in a prompt-based manner. In
short, the proposed Tailor represents each attribute as a pre-trained
continuous vector (i.e., single-attribute prompt) and guides the generation of
a fixed PLM switch to a pre-specified attribute. We experimentally find …

arxiv controlled text generation generation text text generation