Counterfactual Off-Policy Training for Neural Dialogue Generation.
Qingfu ZhuWei-Nan ZhangTing LiuWilliam Yang WangPublished in: EMNLP (1) (2020)
Keyphrases
- network architecture
- training samples
- test set
- neural network
- recurrent networks
- training set
- artificial intelligence
- training phase
- learning algorithm
- man machine
- spoken dialogue systems
- mixed initiative
- dialogue system
- associative memory
- semi supervised
- training process
- generation process
- feedforward neural networks
- neural model
- training examples
- human machine
- natural language
- practical reasoning