A Method for Calculating Term Similarity on Large Document Collections.
Wolfgang W. BeinJeffrey S. CoombsKazem TaghvaPublished in: ITCC (2003)
Keyphrases
- similarity measure
- dynamic programming
- high precision
- detection method
- high accuracy
- significant improvement
- preprocessing
- computationally efficient
- clustering method
- synthetic data
- similarity function
- similarity metric
- experimental evaluation
- computational cost
- probabilistic model
- classification accuracy
- neural network
- mutual information
- support vector machine svm
- multiscale