PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model

arXiv:2306.02531v3 Announce Type: replace
Abstract: Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to exposure bias - the difference between how a model is trained, and how it is used during inference. Denoising diffusion models provide an alternative approach in which a model can revisit and revise its output. However, they can be computationally expensive and prior efforts on text have led to models that …

abstract arxiv autoregressive models bias cs.cl denoising difference diffusion diffusion model diffusion models errors generate inference issue language low quality text type via