A Method of Describing Document Contents through Topic Selection.
Alexander F. GelbukhGrigori SidorovAdolfo Guzmán-ArenasPublished in: SPIRE/CRIWG (1999)
Keyphrases
- detection method
- high accuracy
- high precision
- objective function
- significant improvement
- database
- similarity measure
- clustering method
- preprocessing
- computational cost
- support vector machine
- information retrieval systems
- cost function
- text content
- text mining
- computational complexity
- metadata
- genetic algorithm
- neural network