Hierarchical Reinforcement Learning and Hidden Markov Models for Task-Oriented Natural Language Generation.
Nina DethlefsHeriberto CuayáhuitlPublished in: ACL (2) (2011)
Keyphrases
- hidden markov models
- natural language generation
- hierarchical reinforcement learning
- dialogue system
- reinforcement learning
- natural language
- speech recognition
- model free
- markov models
- machine translation
- sequential data
- state abstraction
- baum welch
- hidden state
- hidden states
- human users
- conditional random fields
- natural language processing
- continuous hidden markov models
- markov model
- reward function
- genetic algorithm
- user model
- markov decision processes
- artificial intelligence