Robust Rule-Based Method for Automatic Break Assignment in Russian Texts.
Ilya OparinPublished in: TSD (2005)
Keyphrases
- experimental evaluation
- fully automatic
- detection method
- similarity measure
- dynamic programming
- high accuracy
- computational complexity
- highly accurate
- high precision
- segmentation method
- cost function
- clustering method
- optimization algorithm
- data driven
- synthetic data
- support vector machine svm
- computationally efficient
- significant improvement
- theoretical analysis
- knowledge base
- markov random field
- classification accuracy
- semi automatic
- prior knowledge
- pairwise
- preprocessing
- image noise