E14-4034 |
considered derivations during
|
k-best parsing
|
. Given two derivations with
|
D13-1064 |
these translations . Incorporating
|
K-Best parsing
|
into our pipeline may help mitigate
|
D09-1059 |
parses , not only the best one . In
|
k-best parsing
|
, we maintain a k-best list in
|
E14-4034 |
. This is done with a top-down
|
k-best parsing
|
algorithm . Finally , the translation
|
J15-3002 |
document-level ; Table 8 shows the
|
k-best parsing
|
results of TSP 1S-1S on the RST
|
P09-1108 |
side . We examine the cost of
|
k-best parsing
|
in the source side of such grammars
|
P09-1108 |
. Since the bottom-up pass of
|
k-best parsing
|
is the bottleneck , we also examine
|
P09-1108 |
time spent in the 1-best phase of
|
k-best parsing
|
. As a base - line , we compared
|
P08-1023 |
forest-based algorithms based on
|
k-best parsing
|
( Huang and Chiang , 2005 ) .
|
P10-1033 |
found to be well handled by the
|
K-Best parsing
|
method in Huang and Chiang (
|
P07-1019 |
approaches for this problem based on
|
k-best parsing
|
algorithms and demonstrate their
|
P11-1125 |
efficient forest-based algorithms for
|
k-best parsing
|
( Huang and Chiang , 2005 ) .
|
C96-2185 |
ranking the parse trees to get
|
k-best parsing
|
re - sults . Its current accuracy
|
P14-2107 |
monotonicity property . Based on it ,
|
k-best parsing
|
merges k-best subtrees in the
|
P08-1067 |
derivations at each node , and uses the
|
k-best parsing
|
Algorithm 2 of Huang and Chiang
|
P07-1019 |
items at each node , and uses the
|
k-best parsing
|
Algorithm 2 of Huang and Chiang
|
J15-3002 |
test set as a function of k of
|
k-best parsing
|
. The 1-best result tells that
|
P12-1064 |
approximate algorithms . In terms of
|
k-best parsing
|
, Huang and Chiang ( 2005 ) proposed
|
N06-3004 |
large . Previous algorithms for
|
k-best parsing
|
( Collins , 2000 ; Charniak and
|
P09-1108 |
efficient known algorithm for
|
k-best parsing
|
( Jim ´ enez and Marzal
|