Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank.
Mouxiang ChenChenghao LiuZemin LiuZhuo LiJianling SunPublished in: CoRR (2023)
Keyphrases
- learning to rank
- ranking functions
- information retrieval
- loss function
- evaluation measures
- document retrieval
- collaborative filtering
- evaluation metrics
- direct optimization
- learning to rank algorithms
- test collection
- ranking svm
- exploration exploitation dilemma
- relevance judgments
- retrieval systems
- pairwise
- similarity measure
- learning algorithm