Latent contextual indexing of annotated documents.
Christian SengstockMichael GertzPublished in: WWW (Companion Volume) (2012)
Keyphrases
- information retrieval
- word spotting
- index terms
- document indexing
- document collections
- document processing
- document analysis
- information retrieval systems
- retrieval engine
- manually constructed
- document retrieval
- database
- text retrieval
- document clustering
- relevant documents
- effective retrieval
- inverted index
- probabilistic retrieval
- contextual information
- manually annotated
- latent dirichlet
- document classification
- latent semantic
- latent topics
- web documents
- text documents
- context sensitive
- chinese text retrieval
- metadata
- xml documents
- retrieval systems
- latent dirichlet allocation
- controlled vocabulary
- multimedia databases
- bibliographic databases
- free text
- textual descriptions
- user queries
- indexing techniques
- document space
- content based retrieval
- vector space model
- retrieval process