A SVMs (Support Vector Machines) based method to identify Chinese place names is presented. In our approach, place name candidate is located according to a rational forming assumption, then SVMs based identification s...A SVMs (Support Vector Machines) based method to identify Chinese place names is presented. In our approach, place name candidate is located according to a rational forming assumption, then SVMs based identification strategy is used to distinguish whether one candidate is true place name or not. Referring to linguistic knowledge, basic semanteme of a contextual word and frequency information of words inside place name candidate are selected as features in our methodology. So dimension in the feature space is reduced dramatically and processing procedure is performed more efficiently. Result of open testing on unregistered place names achieves F-measure 83.25 in 8.17 million words news based on this project.展开更多
This letter investigates an improved blind source separation algorithm based on Maximum Entropy （ME） criteria. The original ME algorithm chooses the fixed exponential or sigmoid ftmction as the nonlinear mapping fun...This letter investigates an improved blind source separation algorithm based on Maximum Entropy （ME） criteria. The original ME algorithm chooses the fixed exponential or sigmoid ftmction as the nonlinear mapping function which can not match the original signal very well. A parameter estimation method is employed in this letter to approach the probability of density function of any signal with parameter-steered generalized exponential function. An improved learning rule and a natural gradient update formula of unmixing matrix are also presented. The algorithm of this letter can separate the mixture of super-Gaussian signals and also the mixture of sub-Gaussian signals. The simulation experiment demonstrates the efficiency of the algorithm.展开更多
基金Foundation of China(Grant No.60175020and60673037) and the National High Technology Research and Development Program of China (Grant No.2002AA117010-09).
文摘A SVMs (Support Vector Machines) based method to identify Chinese place names is presented. In our approach, place name candidate is located according to a rational forming assumption, then SVMs based identification strategy is used to distinguish whether one candidate is true place name or not. Referring to linguistic knowledge, basic semanteme of a contextual word and frequency information of words inside place name candidate are selected as features in our methodology. So dimension in the feature space is reduced dramatically and processing procedure is performed more efficiently. Result of open testing on unregistered place names achieves F-measure 83.25 in 8.17 million words news based on this project.
文摘This letter investigates an improved blind source separation algorithm based on Maximum Entropy （ME） criteria. The original ME algorithm chooses the fixed exponential or sigmoid ftmction as the nonlinear mapping function which can not match the original signal very well. A parameter estimation method is employed in this letter to approach the probability of density function of any signal with parameter-steered generalized exponential function. An improved learning rule and a natural gradient update formula of unmixing matrix are also presented. The algorithm of this letter can separate the mixture of super-Gaussian signals and also the mixture of sub-Gaussian signals. The simulation experiment demonstrates the efficiency of the algorithm.
