J99-4003 in Figure 2 is 01011100 . The decision tree algorithm can ask which partition a tag
E97-1033 with sparseness of data . The decision tree algorithm starts with all of the training
J99-4003 most important aspects of using a decision tree algorithm is the form of the questions
E12-1057 the implementation of the IGTree decision tree algorithm in TiMBL ( Daele - mans et al.
D08-1110 a modified version of the ID3 decision tree algorithm ( Quinlan , 1986 ) , which provides
J99-4003 that encodes the POS tags for the decision tree algorithm . included , such as both the
J11-1006 evaluation ( CFS ; Hall 2000 ) and a decision tree algorithm ( rule - based SL ) . We also
E97-1033 1984 ; Bahl et al. , 1989 ) . The decision tree algorithm has the advantage that it uses
C94-2160 performance of both the rule-based and decision tree algorithms . THE PARSODY SYSTEM Our approach
D10-1110 x ) We employ Gradient Boosted Decision Tree algorithm ( Friedman , 2001 ) to learn
C04-1133 instance-based k-Nearest Neighbor , and a decision tree algorithm ( a version of ID3 ) . For these
D09-1054 answer , plain ) . C4 .5 . This decision tree algorithm solved the same classification
J14-4004 set , and the settings of the decision tree algorithm . The number of feature templates
A00-1024 than to argue for a particular decision tree algorithm , we omit further details of
D09-1056 predictive power of PWA with a Decision Tree algorithm . The remainder of the paper
J06-2001 vector descriptions were fed into a decision tree algorithm . Compared with a baseline performance
J99-4003 second held-out dataset . Using the decision tree algorithm to estimate probabilities is
H01-1009 NE-system which is based on a decision tree algorithm -LSB- 5 -RSB- for the latter
J99-4003 richness of the information that the decision tree algorithm is allowed to use in estimating
D09-1056 WePS-2 data for testing . The Decision Tree algorithm was chosen because we have a
hide detail