P09-2073 |
semantic trees . In this context ,
|
Tree Edit Distance
|
( TED ) has been widely used
|
N13-1106 |
optimal edit script with the lowest
|
tree edit distance
|
. The approach explores both
|
E06-1036 |
should therefore be possible . 4.5
|
Tree edit distance
|
The algorithm was applied using
|
D11-1036 |
δ of a parse are based on
|
tree edit distance
|
( TED ) instead . TED - would
|
E06-1036 |
difficult , especially for the
|
tree edit distance
|
. The syntactic structure has
|
P09-2073 |
Automatic Cost Estimation for
|
Tree Edit Distance
|
Using Particle Swarm Optimization
|
D13-1044 |
Smith , 2010 ) develop an improved
|
Tree Edit Distance
|
( TED ) model for learning tree
|
N13-1070 |
by the fact that the relative
|
tree edit distance
|
between translations of different
|
D08-1032 |
Kouylekov and Magnini , 2005 ) use the
|
tree edit distance
|
algorithms on the dependency
|
D11-1036 |
Finally , we define scores based on
|
tree edit distance
|
, refined to consider the distance
|
N13-1106 |
incorporated through features based on
|
Tree Edit Distance
|
( TED ) . Our model is free of
|
N13-1106 |
total summed cost known as the
|
tree edit distance
|
. Basic edit operations include
|
D09-1130 |
represented by trees ; hence we use a "
|
tree edit distance
|
" for calculating d ( xi , xj
|
P06-1146 |
, we will investigate minimal
|
tree edit distance
|
( Bille , 2005 ) and related
|
N13-1106 |
alignV , proper nouns alignProper 2
|
Tree Edit Distance
|
Model Tree Edit Distance ( §
|
K15-1033 |
Schwartz et al. , 2011 ) , and
|
tree edit distance
|
( TED ) ( Tsarfaty et al. , 2011
|
I05-5003 |
2005 ) applied both a word and
|
tree edit distance
|
algorithm . In this paper we
|
N10-1145 |
popular method for such tasks is
|
Tree Edit Distance
|
( TED ) , which models sentence
|
N13-1106 |
Extraction as Sequence Tagging with
|
Tree Edit Distance
|
</title> Yao Van_Johns Hopkins
|
E12-1006 |
an evaluation measure based on
|
tree edit distance
|
( TED ) which discards edit operations
|