Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarization.
Siyao LiDeren LeiPengda QinWilliam Yang WangPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- model free
- state space
- reinforcement learning algorithms
- semantic annotation
- multi agent
- partially observable
- optimal policy
- learning process
- natural language
- function approximators
- machine learning
- semantic knowledge
- control policy
- semantic search
- action selection
- reward shaping
- multiarmed bandit
- optimal control
- semantic network
- semantic web
- domain specific
- co occurrence
- high level
- learning algorithm
- semantic analysis
- semantic similarity
- temporal difference
- low level features
- semantic content
- markov decision process
- web services
- neural network