On the measurement of test collection reliability.
Julián UrbanoMónica MarreroDiego MartínPublished in: SIGIR (2013)
Keyphrases
- test collection
- information retrieval
- retrieval model
- search tasks
- retrieval effectiveness
- language model
- document collections
- retrieval systems
- relevant documents
- average precision
- ir evaluation
- relevance judgments
- relevance assessments
- chinese web
- relevance judgements
- evaluation of information retrieval systems
- evaluation methodology
- learning to rank
- trec test collections
- document set
- search engine
- newspaper articles
- databases
- evaluation campaigns
- trec web
- website
- active learning