Simulating Bandit Learning from User Feedback for Extractive Question Answering.
Ge GaoEunsol ChoiYoav ArtziPublished in: CoRR (2022)
Keyphrases
- question answering
- user feedback
- user interaction
- learning algorithm
- information extraction
- information retrieval
- qa clef
- learning process
- question classification
- text summarization
- reinforcement learning
- natural language
- named entities
- natural language questions
- syntactic information
- natural language processing
- supervised learning
- database systems
- artificial intelligence