Deep Reinforcement Learning for NLP.
William Yang WangJiwei LiXiaodong HePublished in: ACL (5) (2018)
Keyphrases
- reinforcement learning
- natural language processing
- function approximation
- model free
- natural language
- optimal control
- information extraction
- reinforcement learning algorithms
- machine translation
- state space
- question answering
- optimal policy
- wordnet
- language processing
- data sets
- semantic analysis
- natural language understanding
- machine learning
- dynamic programming
- hidden markov models
- text mining
- robotic control
- transition model
- autonomous learning
- learning algorithm
- temporal difference
- action selection
- markov decision processes
- expert systems
- learning process
- free text
- multi agent
- mobile robot
- robot control
- stochastic approximation
- learning problems
- transfer learning
- field of natural language processing