Retrieval from Noisy E-Discovery Corpus in the Absence of Training Data.
Anirban ChakrabortyKripabandhu GhoshSwapan Kumar ParuiPublished in: SIGIR (2015)
Keyphrases
- training data
- noisy data
- test set
- information retrieval
- image database
- information retrieval systems
- decision trees
- image retrieval
- data sets
- test data
- content based retrieval
- training corpus
- learning algorithm
- retrieval process
- training process
- incomplete data
- multimedia databases
- document level
- classification accuracy
- training set
- manually annotated
- document retrieval
- retrieval model
- support vector machine
- sentence level
- similar documents
- enterprise search
- evaluation methods
- training samples
- query expansion
- supervised learning
- relevance feedback
- prior knowledge
- multimedia