Using Multiple Query Aspects to Build Test Collections without Human Relevance Judgments.
Miles EfronPublished in: ECIR (2009)
Keyphrases
- test collection
- human relevance judgments
- relevance judgments
- language model
- retrieval systems
- web search engines
- average precision
- precision recall
- relevant documents
- information retrieval
- retrieval effectiveness
- queries and relevance judgments
- ad hoc retrieval
- relevance assessments
- retrieval model
- relevance judgements
- document collections
- information retrieval evaluation
- learning to rank
- relevance feedback
- evaluation methodology
- web search
- user queries
- document set
- search engine
- patent retrieval
- user feedback
- query expansion
- xml retrieval
- evaluation measures
- ranking functions
- user interaction
- information retrieval systems
- probabilistic model
- user interface
- ir evaluation
- multimedia
- clef evaluation campaign
- web pages