基于支持向量机和转换的错误驱动学习方法的组块识别

SVM-based chunk recognition and transformation-based error-driver learning

支持向量机在高维特征空间的输入数据上具有较高的泛化性能,能够独立于小范围内的数据维数计算.基于转换的学习方法能自动融合不同类型的知识,所得到的模板可以显示一些语言知识,这些语言知识对于语言学及其他相关研究有重要意义.利用支持向量机和基于转换的错误驱动学习相结合,能够达到较为满意的组块识别效果.

The paper presents a method of Chinese chunk recognition based on Support Vector Machines （SVM） and transformation-based error-driven learning. It is well known that SVM is good at achieving high generalization of very high dimensional feature space. SVM can be trained in a high dimensional space with smaller computational cost independent of their dimensionalities. Transformation-based learning method can combine many kinds features and express much knowledge of linguistic which is very important to other research. Using SVM method and Trans- formation-based learning method can combine the advantages and get a satisfaction of identification.