Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training.
Wangchunshu ZhouQifei LiChenle LiPublished in: CoRR (2021)
Keyphrases
- learning algorithm
- learning process
- online learning
- learning speed
- feedforward neural networks
- learning systems
- structured prediction
- reinforcement learning
- learning stage
- active learning
- hidden markov models
- motor skills
- prior knowledge
- multi agent
- data sets
- neural network
- minimum error rate
- recurrent networks
- human computer
- training process
- learning tasks
- unsupervised learning
- training data