Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards.
Hou Pong ChanWang ChenLu WangIrwin KingPublished in: ACL (1) (2019)
Keyphrases
- reinforcement learning
- markov decision processes
- adaptive behavior
- fitted q iteration
- function approximation
- adaptive control
- neural network
- machine learning
- network architecture
- model free
- reinforcement learning algorithms
- state space
- optimal policy
- learning algorithm
- learning capabilities
- reward function
- action space
- multi agent
- bio inspired
- generation process
- keyphrases
- policy iteration
- dynamic programming
- temporal difference
- artificial neural networks
- search results clustering
- information retrieval