On Aggregating Labels from Multiple Crowd Workers to Infer Relevance of Documents.
Mehdi HosseiniIngemar J. CoxNatasa Milic-FraylingGabriella KazaiVishwa VinayPublished in: ECIR (2012)
Keyphrases
- information retrieval
- information retrieval systems
- document collections
- highly relevant
- metadata
- document clustering
- relevance ranking
- retrieved documents
- relevant documents
- document relevance
- combining multiple
- text documents
- test collection
- web documents
- text categorization
- information technology
- relevance judgements
- structured document retrieval
- structured documents
- document classification
- ranked list
- document retrieval
- text classification
- text mining
- relevance feedback
- xml documents
- pairwise
- training data
- clustering algorithm
- feature selection