CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation
arXiv:1911.06641
Abstract
Generating multiple categories of texts is a challenging task and draws more and more attention. Since generative adversarial nets (GANs) have shown competitive results on general text generation, they are extended for category text generation in some previous works. However, the complicated model structures and learning strategies limit their performance and exacerbate the training instability. This paper proposes a category-aware GAN (CatGAN) which consists of an efficient category-aware model for category text generation and a hierarchical evolutionary learning algorithm for training our model. The category-aware model directly measures the gap between real samples and generated samples on each category, then reducing this gap will guide the model to generate high-quality category samples. The Gumbel-Softmax relaxation further frees our model from complicated learning strategies for updating CatGAN on discrete data. Moreover, only focusing on the sample quality normally leads the mode collapse problem, thus a hierarchical evolutionary learning algorithm is introduced to stabilize the training procedure and obtain the trade-off between quality and diversity while training CatGAN. Experimental results demonstrate that CatGAN outperforms most of the existing state-of-the-art methods.
arXiv comment15 pages, 4 figures. Accepted by AAAI 2020
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Categorical Reparameterization with Gumbel-Softmax
- Convolutional Neural Networks for Sentence Classification
- The relativistic discriminator: a key element missing from standard GAN
- Adversarial Learning for Neural Dialogue Generation
- How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
- Long Text Generation via Adversarial Training with Leaked Information
- Texygen: A Benchmarking Platform for Text Generation Models
- REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
- Language GANs Falling Short
- On Accurate Evaluation of GANs for Language Generation
- Adversarial Text Generation via Feature-Mover's Distance
- Relational recurrent neural networks
- Neural Machine Translation with Gumbel-Greedy Decoding