Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards.
Hou Pong ChanWang ChenLu WangIrwin KingPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- fitted q iteration
- markov decision processes
- adaptive control
- function approximation
- neural network
- state space
- temporal difference
- adaptive behavior
- reward function
- keyphrase extraction
- learning capabilities
- reinforcement learning algorithms
- learning algorithm
- generation process
- reward shaping
- model free
- multi agent
- network architecture
- function approximators
- machine learning
- optimal control
- action space
- partial observability
- optimal policy