Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation. (arXiv:2109.06513v2 [cs.CL] UPDATED)

Dialog models can be greatly strengthened through grounding on various
external information, but grounded dialog corpora are usually not naturally
accessible. In this work, we focus on the few-shot learning for grounded dialog
generation (GDG). We first propose a simple prompting method for GDG tasks,
where different constructs of model input, such as the grounding source and the
conversation context, are distinguished through continuous or discrete prompts.
On three typical GDG tasks, we empirically demonstrate and analyze in-depth the
effectiveness …

arxiv few-shot learning learning