Computational linguistics for metadata building (CLiMB): using text mining for the automatic identification, categorization, and disambiguation of subject terms for image metadata.
Judith L. KlavansCarolyn SheffieldEileen G. AbelsJimmy LinRebecca J. PassonneauTandeep SidhuDagobert SoergelPublished in: Multim. Tools Appl. (2009)
Keyphrases
- metadata
- computational linguistics
- automatic identification
- text mining
- natural language processing
- textual descriptions
- digital libraries
- artificial intelligence
- input image
- co occurrence
- information extraction
- information retrieval
- multiscale
- image structure
- text documents
- wordnet
- image segmentation
- knowledge representation
- text corpora
- data mining
- segmentation method
- feature points
- text classification
- data analysis
- machine learning
- databases
- edge detection
- text categorization
- knowledge discovery
- computer science
- cross language information retrieval
- barcode
- natural language
- knowledge base
- ontology construction