Simulating Bandit Learning from User Feedback for Extractive Question Answering.
Ge GaoEunsol ChoiYoav ArtziPublished in: ACL (1) (2022)
Keyphrases
- question answering
- user feedback
- learning process
- information extraction
- user interaction
- information retrieval
- learning algorithm
- artificial intelligence
- natural language
- cross language
- active learning
- named entities
- question classification
- question answering systems
- user profiles
- supervised learning
- reinforcement learning