Style Example-Guided Text Generation using Generative Adversarial Transformers

Abstract

We introduce a language generative model framework for generating a styled paragraph based on a context sentence and a style reference example. The framework consists of a style encoder and a texts decoder. The style encoder extracts a style code from the reference example, and the text decoder generates texts based on the style code and the context. We propose a novel objective function to train our framework. We also investigate different network design choices. We conduct extensive experimental validation with comparison to strong baselines to validate the effectiveness of the proposed framework using a newly collected dataset with diverse text styles. Both code and dataset will be released upon publication.

References in corpus (7)

• Distilling the Knowledge in a Neural Network
• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• A Learned Representation For Artistic Style
• Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
• Insertion Transformer: Flexible Sequence Generation via Insertion Operations
• KERMIT: Generative Insertion-Based Modeling for Sequences