How Large a Corpus Do We Need: Statistical Method Versus Rule-based Method.
Hai ZhaoYan SongChunyu KitPublished in: LREC (2010)
Keyphrases
- high accuracy
- computational cost
- support vector machine svm
- main contribution
- significant improvement
- synthetic data
- detection method
- fully automatic
- cost function
- prior knowledge
- preprocessing
- multiscale
- edge detection
- segmentation method
- computational complexity
- data sets
- classification method
- optimization method
- error rate
- theoretical analysis
- computationally efficient
- mutual information
- classification accuracy