Combined Word-Spacing Method for Disambiguating Korean Texts.
Mi-young KangAe-sun YoonHyuk-Chul KwonPublished in: Australian Conference on Artificial Intelligence (2004)
Keyphrases
- high accuracy
- machine learning
- similarity measure
- preprocessing
- segmentation method
- synthetic data
- clustering method
- high precision
- pairwise
- significant improvement
- cost function
- computational cost
- co occurrence
- natural language text
- data sets
- classification method
- segmentation algorithm
- feature set
- classification accuracy
- dynamic programming
- prior knowledge
- computational complexity
- neural network