564 search results - page 59 / 113 » Training Tree Transducers |
147
click to vote
EMNLP
2009
14 years 11 months ago
2009
We connect two scenarios in structured learning: adapting a parser trained on one corpus to another annotation style, and projecting syntactic annotations from one language to ano...
109
click to vote
CVPR
2010
IEEE
15 years 10 months ago
2010
IEEE
We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled f...
114
click to vote
LATA
2010
Springer
15 years 8 months ago
2010
Springer
We extend stochastic context-free grammars such that the probability of applying a production can depend on the length of the subword that is generated from the application and sho...
100
click to vote
ICPR
2008
IEEE
15 years 8 months ago
2008
IEEE
In online handwritten math expression recognition, one-pass dynamic programming can produce highquality symbol graphs in addition to best symbol sequence hypotheses [3], especiall...
IDA
2007
Springer
15 years 8 months ago
2007
Springer
Random forests are one of the best performing methods for constructing ensembles. They derive their strength from two aspects: using random subsamples of the training data (as in b...