DiffuCOMET: Contextual Commonsense Knowledge Diffusion

arXiv:2402.17011v1 Announce Type: new
Abstract: Inferring contextually-relevant and diverse commonsense to understand narratives remains challenging for knowledge models. In this work, we develop a series of knowledge models, DiffuCOMET, that leverage diffusion to learn to reconstruct the implicit semantic connections between narrative contexts and relevant commonsense knowledge. Across multiple diffusion steps, our method progressively refines a representation of commonsense facts that is anchored to a narrative, producing contextually-relevant and diverse commonsense inferences for an input context. To evaluate DiffuCOMET, we …

abstract arxiv cs.cl diffusion diverse knowledge learn multiple narrative semantic series type work