Using reinforcement learning with external rewards for open-domain natural language generation.
Vidhushini SrinivasanSashank SanthanamSamira ShaikhPublished in: J. Intell. Inf. Syst. (2021)
Keyphrases
- natural language generation
- open domain
- reinforcement learning
- information extraction
- natural language processing
- natural language
- markov decision processes
- question answering
- machine translation
- dialogue system
- text generation
- dialog systems
- question answering systems
- word order
- state space
- machine learning
- reward function
- optimal policy
- multi agent
- reinforcement learning algorithms
- wordnet