Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

by   Zhihong Shao, et al.

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.


page 1

page 2

page 3

page 4


Data-to-text Generation with Variational Sequential Planning

We consider the task of data-to-text generation, which aims to create te...

Hierarchical Text Generation and Planning for Strategic Dialogue

End-to-end models for strategic dialogue are challenging to train, becau...

Plan-then-Generate: Controlled Data-to-Text Generation via Planning

Recent developments in neural networks have led to the advance in data-t...

Learning to Select, Track, and Generate for Data-to-Text

We propose a data-to-text generation model with two modules, one for tra...

Sentence-Permuted Paragraph Generation

Generating paragraphs of diverse contents is important in many applicati...

GGP: A Graph-based Grouping Planner for Explicit Control of Long Text Generation

Existing data-driven methods can well handle short text generation. Howe...

Knowledge-based Review Generation by Coherence Enhanced Text Planning

As a natural language generation task, it is challenging to generate inf...