Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System.
Chang TianWenpeng YinMarie-Francine MoensPublished in: NAACL-HLT (Findings) (2022)
Keyphrases
- dialogue system
- human computer
- tutorial dialogue
- dialogue management
- learning algorithm
- learning process
- natural language understanding
- human robot
- spoken dialogue systems
- spoken language
- machine learning
- natural language
- mixed initiative
- action selection
- context aware
- knowledge acquisition
- training data
- dialogue manager