Self-Adversarial Learning with Comparative Discrimination for Text Generation
arXiv:2001.11691
Abstract
Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples. To address the issues, we propose a novel self-adversarial learning (SAL) paradigm for improving GANs' performance in text generation. In contrast to standard GANs that use a binary classifier as its discriminator to predict whether a sample is real or generated, SAL employs a comparative discriminator which is a pairwise classifier for comparing the text quality between a pair of samples. During training, SAL rewards the generator when its currently generated sentence is found to be better than its previously generated samples. This self-improvement reward mechanism allows the model to receive credits more easily and avoid collapsing towards the limited number of real samples, which not only helps alleviate the reward sparsity issue but also reduces the risk of mode collapse. Experiments on text generation benchmark datasets show that our proposed approach substantially improves both the quality and the diversity, and yields more stable performance compared to the previous GANs for text generation.
ICLR 2020
References in corpus (10)
- Continuous control with deep reinforcement learning
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Exploring the Limits of Language Modeling
- The relativistic discriminator: a key element missing from standard GAN
- GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
- Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
- Adversarial Ranking for Language Generation
- On distinguishability criteria for estimating generative models
- Adversarial Text Generation via Feature-Mover's Distance
Cited by in corpus (4)
- Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
- To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs
- Adaptive Bridge between Training and Inference for Dialogue
- Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training