chinese word 0.00282035
alignment model 0.00244114
chinese ner 0.002337404
chinese nes 0.0022466129999999997
english word 0.00224519
word alignment 0.00220119
chinese org 0.0021887449999999998
chinese character 0.002120415
chinese string 0.0021138859999999997
chinese component 0.0020553299999999997
chinese sentence 0.0020166439999999997
chinese characters 0.002015804
chinese netype 0.001999828
english words 0.001997921
chinese sentences 0.001977941
chinese charac 0.00197715
statistical model 0.001973127
ner model 0.001972364
alignment performance 0.00192003
translation model 0.001894632
above model 0.0017913340000000001
recognition model 0.001774923
english ner 0.001762244
feature information 0.001747898
joint model 0.001722362
good model 0.001718238
chinese 0.00171267
bigram model 0.001673587
english nes 0.001671453
model con 0.001652814
oint model 0.001635399
proposed model 0.001613849
english org 0.001613585
bilingual alignment 0.0016119390000000002
adopted model 0.0016109380000000001
derived model 0.0016109380000000001
model incor 0.0016109380000000001
other language 0.001565172
distance information 0.0015236870000000001
alignment accuracy 0.001508007
english side 0.0015051420000000001
alignment task 0.001490961
transliteration mappings 0.001484192
alignment joint 0.001468242
same type 0.0014566029999999999
ner system 0.0014519720000000002
alignment stage 0.001451947
alignment factors 0.001450322
english pronunciation 0.0014429
english sentence 0.001441484
final alignment 0.001440702
english characters 0.001440644
transliteration cost 0.001440373
english part 0.00143128
word unit 0.001429792
linguistic data 0.0014185209999999998
english counterpart 0.001404045
english sentences 0.001402781
english sides 0.001400923
language pairs 0.001400536
alignment factor 0.0013843100000000001
baseline alignment 0.001375299
word segmen 0.001373731
language modeling 0.001370707
gual alignment 0.0013641270000000001
monolingual information 0.001360197
alignment module 0.001356924
model 0.00134763
same test 0.001334719
broadcast information 0.001328517
training set 0.0013282699999999999
information service 0.001322978
initial performance 0.001269851
language processing 0.001262109
relative error 0.001249949
language pair 0.001249011
same expansion 0.00124334
data con 0.001231447
main data 0.001229721
linguistic feature 0.001227376
mapping type 0.001223935
bilingual type 0.001221238
above error 0.001209762
tokenized language 0.001208051
candidate set 0.001207449
sri language 0.001201686
important feature 0.001201166
good performance 0.001197128
unlabeled data 0.001189908
error rate 0.001188802
rate training 0.001180772
org type 0.001178884
person names 0.001162454
entity type 0.001162409
transliteration 0.00115646
low performance 0.00115264
name entity 0.001140651
basic system 0.001139336
english 0.00113751
rtype type 0.0011351669999999999
