Promptly Predicting Structures: The Return of Inference

arXiv:2401.06877v2 Announce Type: replace
Abstract: Prompt-based methods have been used extensively across NLP to build zero- and few-shot label predictors. Many NLP tasks are naturally structured: that is, their outputs consist of multiple labels which constrain each other. Annotating data for such tasks can be cumbersome. Can the promise of the prompt-based paradigm be extended to such structured outputs? In this paper, we present a framework for constructing zero- and few-shot linguistic structure predictors. Our key insight is that we …

abstract arxiv build cs.cl data few-shot inference labels multiple nlp paradigm prompt tasks the prompt type