Ranking Like Human: Global-View Matching via Reinforcement Learning for Answer Selection.
Yingxue ZhangPing JianRuiying GengYuansheng SongFandong MengPublished in: IALP (2019)
Keyphrases
- global view
- reinforcement learning
- matching process
- ranking algorithm
- matching algorithm
- pattern matching
- web search
- graph matching
- short list
- machine learning
- shape matching
- optimal policy
- ranking functions
- learning to rank
- human subjects
- function approximation
- multi agent
- similarity assessment
- keypoints
- decision makers
- state space
- high dimensional
- correct answers
- human judgments
- decision making