Advanced Training Set Construction for Retrieval in Historic Documents.
Andrea Ernst-GerlachNorbert FuhrPublished in: AIRS (2010)
Keyphrases
- training set
- information retrieval
- information retrieval systems
- document retrieval
- retrieval systems
- structured documents
- document indexing
- retrieval engine
- document analysis
- document collections
- expert finding
- relevant documents
- heterogeneous collections
- text retrieval
- test collection
- image database
- training data
- document content
- multimedia documents
- document ranking
- query terms
- retrieval strategies
- retrieval model
- automatic categorization
- retrieval process
- test set
- interactive retrieval
- index terms
- document level
- nearest neighbor
- effective retrieval
- cultural heritage
- document structure
- web documents
- web retrieval
- retrieved documents
- metadata
- data sets
- vector space model
- text collections
- xml documents
- active learning
- query expansion
- text queries
- boolean queries
- supervised learning
- classification accuracy
- relevance assessments
- documents retrieved
- image retrieval
- similar documents
- text documents
- decision trees
- user queries
- relevance ranking
- semantic content
- handwritten documents
- distributed information retrieval
- monolingual retrieval
- retrieve documents
- related documents
- content and structure
- relevance model
- xml retrieval
- average precision
- document representation
- content based retrieval
- text categorization
- language model
- web search
- keywords