W06-2904 |
two ideas for improving large
|
margin training
|
in the context of dependency
|
N07-3002 |
approach , I improve structured large
|
margin training
|
for parsing in two ways ( Wang
|
D12-1051 |
chunks . A relaxed , online maximum
|
margin training
|
algorithm is used for learning
|
P08-1061 |
semi-supervised structured large
|
margin training
|
. Unlike previous proposed approaches
|
N07-3002 |
currently being used in large
|
margin training
|
algorithms . In the second approach
|
P08-1061 |
proposed semi-supervised large
|
margin training
|
algorithm outperforms the supervised
|
W06-2904 |
discussing our modifications to large
|
margin training
|
for parsing in detail , we first
|
N12-1013 |
softmax-margin . MLE and softmax -
|
margin training
|
were statistically indistinguishable
|
P08-1061 |
the supervised structured large
|
margin training
|
approach in the experiments in
|
W06-2904 |
for future research . 4 Large
|
Margin Training
|
Given a training set of sentences
|
N12-1023 |
al. , 2006 ) , an online large -
|
margin training
|
algorithm . It has recently shown
|
W06-2904 |
give a brief overview of large
|
margin training
|
, and then present our two modifications
|
J14-4004 |
usual in such methods , the large
|
margin training
|
improves the quality of the learned
|
D10-1059 |
investigate a perceptron-like online
|
margin training
|
for statisit - ical machine translation
|
N07-3002 |
appears to have culminated in large
|
margin training
|
approaches ( Taskar et al. ,
|
N07-3002 |
not being used in current large
|
margin training
|
algorithms . Another unexploited
|
P08-1061 |
semi-supervised structured large
|
margin training
|
, and an efficient training algorithm
|
P08-1061 |
application of the structured large
|
margin training
|
approach first proposed in (
|
D12-1051 |
is a relaxed , online maximum
|
margin training
|
algorithm with the desired accuracy
|
P08-1061 |
Training Supervised structured large
|
margin training
|
approaches have been applied
|