Incorporating Diversity and Density in Active Learning for Relevance Feedback.
Zuobing XuRam AkellaYi ZhangPublished in: ECIR (2007)
Keyphrases
- relevance feedback
- active learning
- document retrieval
- information retrieval systems
- query expansion
- learning algorithm
- maximal marginal relevance
- user feedback
- machine learning
- selective sampling
- retrieval effectiveness
- semi supervised
- relevant documents
- supervised learning
- pseudo relevance feedback
- training examples
- labeled data
- unlabeled data
- image retrieval
- cost sensitive
- low level features
- retrieval model
- learning strategies
- semi supervised learning
- random sampling
- experimental design
- query refinement
- training set
- low density
- user system interaction
- pool based active learning
- multi objective
- sample selection
- information retrieval