J06-3003 experiments use single nearest neighbor classification with leave-one-out cross-validation
W13-2027 rate ) . It relies on a 1-nearest neighbor classification of the noun phrase ( NP ) extracted
W08-0909 used as features for a nearest neighbor classification algorithm . The unigram language
W09-1007 based , approximation of k-nearest neighbor classification ( Knuth , 1973 ; Daelemans et
W06-2604 using SVD . 3.2 The k nearest neighbor classification algorithm ( k-NN ) k-NN is a
D13-1058 improves the accuracy of nearest neighbor classification . We have theoretically analyzed
P11-2009 been proposed to make nearest neighbor classification more efficient ( Angiulli , 2005
W90-0104 based on a variant of nearest neighbor classification ( Center for Machine Translation
N07-1068 naïve OCR system based on nearest neighbor classification algorithms and clustering techniques
D10-1074 classification problem , using a k-nearest neighbor classification model with following features
W05-0701 memory-based learning ( k-nearest neighbor classification ) to morphological analysis and
W06-0901 where maximum entropy and nearest neighbor classification perform very similarly . For
W09-1109 simple model , doing k nearest neighbor classification where the distance between two
W09-1304 classification tasks based on the k-nearest neighbor classification rule ( Cover and Hart , 1967
W09-1105 classification tasks based on the k-nearest neighbor classification rule ( Cover and Hart , 1967
E03-1051 essentially follows the k-nearest neighbor classification rule ( Cover and Hart , 1967
W12-2034 approximation of memory-based or k-nearest neighbor classification , implemented within the TiMBL2
W04-2407 top of the classical k nearest neighbor classification kernel , such as value distance
C04-1010 top of the classical k nearest neighbor classification kernel , such as value distance
D08-1075 classification tasks based on the k-nearest neighbor classification rule ( Cover and Hart , 1967
hide detail