model training 0.0034748039999999997
language model 0.003297959
different model 0.003195344
word segmentation 0.0031604560000000003
chinese word 0.003074475
network model 0.003046605
same model 0.002987836
work model 0.002937429
new model 0.002915594
model performance 0.002874991
model pku 0.002873991
proper model 0.002828046
local model 0.002823441
crf model 0.002811085
model efficiency 0.0027857949999999998
model suf 0.00276233
model selection 0.0027540539999999997
model outper 0.002752056
model configura 0.002751276
model effi 0.00275028
model boost 0.00275028
word boundary 0.0026981310000000003
word seg 0.002562167
word segmenta 0.002540146
word recall 0.002530193
model 0.00252595
word segmen 0.002517603
nese word 0.0025145460000000003
feature vector 0.0019377819999999999
training data 0.001881054
training corpus 0.001800757
different training 0.001618248
test data 0.001589624
chinese language 0.0015573940000000001
possible features 0.001520141
linear models 0.0014964639999999999
additional features 0.001470965
input feature 0.001467085
feature embeddings 0.001464382
feature representations 0.00145385
training set 0.001453378
bigram features 0.0014504210000000001
training algorithm 0.001441973
statistical features 0.0014338620000000002
additional feature 0.001424405
gram features 0.001419195
common feature 0.001409519
feature dictionary 0.00140881
bigram feature 0.001403861
test results 0.001402853
complex features 0.0013974400000000002
previous tag 0.001394252
other models 0.001391817
discrete feature 0.001389613
tag set 0.001378134
text feature 0.001376858
ditional features 0.0013718
unigram features 0.001371252
total words 0.001371077
network models 0.0013673449999999998
handcrafted features 0.001366514
tag sequence 0.001365347
tag representation 0.001361204
feature embedding 0.0013607049999999998
feature combination 0.001360628
identical words 0.001356322
feature engineering 0.0013562639999999998
segmentation task 0.00134242
tensor function 0.0013382630000000001
minimal feature 0.001326308
unigram feature 0.001324692
manual feature 0.001317941
feature engi 0.001317941
different tensor 0.00130156
msra data 0.001294924
tag score 0.001291797
training time 0.001291331
vector space 0.001286609
training process 0.001271233
score vector 0.001262919
work models 0.001258169
possible tag 0.001254141
tensor neural 0.001253828
tag embeddings 0.001244942
result models 0.001239179
english data 0.001226189
current tag 0.001225612
pos tagging 0.001219394
input vector 0.001218767
training examples 0.001212403
tag dependency 0.001206515
work chinese 0.001196864
unlabeled data 0.001195733
models pku 0.001194731
tensor parameters 0.0011821029999999999
semantic information 0.001180396
table layer 0.00118037
training cases 0.00117322
training instance 0.00117322
symbolic data 0.00116983
