An Exam-based Evaluation Approach Beyond Traditional Relevance Judgments.
Naghmeh FarziLaura DietzPublished in: CoRR (2024)
Keyphrases
- relevance judgments
- test collection
- learning to rank
- average precision
- retrieval effectiveness
- retrieval systems
- user feedback
- web search engines
- evaluation measures
- relevant documents
- relevance feedback
- evaluation metrics
- relevance assessments
- ranking functions
- information retrieval evaluation
- human judgments
- information retrieval systems
- query performance prediction
- search engine
- ranked list
- pairwise
- query difficulty
- reinforcement learning
- human relevance judgments
- precision and recall
- document collections
- web search
- classification accuracy
- learning environment
- information retrieval
- queries and relevance judgments