NeuroLogic Decoding

AbstractConditional text generation often requires lexical constraints, i.e., which words should or shouldn’t be included in the output text. While the dominant recipe for conditional text generation has been large-scale …...

AbstractCommonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative that …...

AbstractText generation often involves producing coherent and grammatically correct texts that also satisfy a given set of semantic constraints. While most approaches for conditional text generation have primarily focused on …...