Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
This addresses the challenge of producing coherent and varied long texts for applications like automated reporting or storytelling, though it appears incremental as it builds on hierarchical and variational methods.
The paper tackled the problem of generating long and diverse texts from data, where existing neural methods struggle with dynamic input modeling, coherence, and diversity, by proposing a Planning-based Hierarchical Variational Model (PHVM) that plans groups of input items and generates sentences hierarchically, resulting in outperforming state-of-the-art baselines.
Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence, or to generate diversified expressions. To address these issues, we propose a Planning-based Hierarchical Variational Model (PHVM). Our model first plans a sequence of groups (each group is a subset of input items to be covered by a sentence) and then realizes each sentence conditioned on the planning result and the previously generated context, thereby decomposing long text generation into dependent sentence generation sub-tasks. To capture expression diversity, we devise a hierarchical latent structure where a global planning latent variable models the diversity of reasonable planning and a sequence of local latent variables controls sentence realization. Experiments show that our model outperforms state-of-the-art baselines in long and diverse text generation.