Modelling Randomness in Relevance Judgments and Evaluation Measures.
Marco FerranteNicola FerroSilvia PontarolloPublished in: ECIR (2018)
Keyphrases
- evaluation measures
- relevance judgments
- learning to rank
- retrieval systems
- precision and recall
- evaluation metrics
- relevance assessments
- benchmark datasets
- human relevance judgments
- web search engines
- information retrieval evaluation
- information retrieval
- clickthrough data
- retrieval effectiveness
- ranked list
- machine learning
- data sets
- ranking functions
- document retrieval
- learning process
- retrieved documents
- feature space
- search engine
- databases