SparseGAN: Sparse Generative Adversarial Network for Text Generation

by   Liping Yuan, et al.

It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategies either suffer from unreliable gradient estimations or imprecise sentence representations. Inspired by the principle of sparse coding, we propose a SparseGAN that generates semantic-interpretable, but sparse sentence representations as inputs to the discriminator. The key idea is that we treat an embedding matrix as an over-complete dictionary, and use a linear combination of very few selected word embeddings to approximate the output feature representation of the generator at each time step. With such semantic-rich representations, we not only reduce unnecessary noises for efficient adversarial training, but also make the entire training process fully differentiable. Experiments on multiple text generation datasets yield performance improvements, especially in sequence-level metrics, such as BLEU.


page 1

page 2

page 3

page 4


ARAML: A Stable Adversarial Training Framework for Text Generation

Most of the existing generative adversarial networks (GAN) for text gene...

Generating Text through Adversarial Training using Skip-Thought Vectors

In the past few years, various advancements have been made in generative...

TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks

Text generation is of particular interest in many NLP applications such ...

Efficient text generation of user-defined topic using generative adversarial networks

This study focused on efficient text generation using generative adversa...

Ruminating Word Representations with Random Noised Masker

We introduce a training method for both better word representation and p...

Alleviate Exposure Bias in Sequence Prediction with Recurrent Neural Networks

A popular strategy to train recurrent neural networks (RNNs), known as “...

An Empirical Study of Extrapolation in Text Generation with Scalar Control

We conduct an empirical evaluation of extrapolation performance when con...