PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
This addresses the issue of exposure bias and computational inefficiency in text generation models, offering a solution for generating fluent and diverse paragraphs, though it appears incremental as it builds on existing diffusion and autoregressive methods.
The authors tackled the problem of repetitive and low-quality text generation in autoregressive models by proposing PLANNER, which combines latent semantic diffusion with autoregressive generation to achieve global control over paragraphs, resulting in effective generation of high-quality long-form text across tasks like semantic generation, text completion, and summarization.
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 produce less fluent output compared to autoregressive models, especially for longer text and paragraphs. In this paper, we propose PLANNER, a model that combines latent semantic diffusion with autoregressive generation, to generate fluent text while exercising global control over paragraphs. The model achieves this by combining an autoregressive "decoding" module with a "planning" module that uses latent diffusion to generate semantic paragraph embeddings in a coarse-to-fine manner. The proposed method is evaluated on various conditional generation tasks, and results on semantic generation, text completion and summarization show its effectiveness in generating high-quality long-form text in an efficient manner.