character word 0.0040216
word segmentation 0.0036695
chinese word 0.0034811959999999998
possible word 0.003235763
current word 0.003212231
corresponding word 0.003127353
word count 0.0030853499999999997
last word 0.003064366
word seg 0.003051641
contextual word 0.003038072
word counts 0.003000793
word trades 0.002947376
rare word 0.002947275
ith word 0.002944914
word segmenta 0.002944157
unconstrained word 0.002943996
preceding word 0.0029419
legal word 0.002940071
word counting 0.00293889
feature model 0.0028464400000000004
pos tag 0.00272064
chinese pos 0.002490846
pos tagging 0.002424585
character tag 0.00241169
pos tags 0.00238637
count features 0.00225664
possible pos 0.002245413
linear model 0.002222625
pos tagger 0.002199673
english pos 0.00219424
chinese character 0.002181896
binary features 0.002168367
morphological features 0.002159273
baseline model 0.0021498380000000003
pos representation 0.0021459160000000003
lookahead features 0.0021398520000000002
morph features 0.002126711
character tagging 0.0021156350000000003
compact features 0.002111925
counting features 0.00211018
character sequence 0.002066523
certain pos 0.002008456
deterministic model 0.0019961700000000002
feature function 0.001975071
pos category 0.001964768
ble pos 0.001958647
pos taging 0.001946468
pos ambi 0.001946468
mine pos 0.001946468
feature set 0.001927761
current character 0.001912931
feature templates 0.001904749
possible words 0.001900803
feature beam 0.001873628
same feature 0.0018622410000000002
input character 0.00185856
probabilistic model 0.0018504880000000002
english words 0.00184963
features 0.00183174
ing character 0.00183131
input words 0.0018229
feature space 0.0018165030000000001
feature representation 0.001810256
training data 0.001792563
training corpus 0.001757594
tag sequence 0.001755913
cws character 0.00175157
new words 0.001750464
basic feature 0.001746624
segmentation sequence 0.001714423
segmentation accuracy 0.001705335
contextual words 0.001703112
binary feature 0.001671067
rich feature 0.0016686270000000002
character sequences 0.001660674
typical character 0.001657917
mapping words 0.0016479659999999998
ith character 0.001645614
unknown words 0.0016443
ery character 0.001642632
lookahead feature 0.001642552
feature tem 0.0016387430000000002
character cij 0.001638156
morph feature 0.001629411
feature sets 0.0016285100000000001
possible tag 0.001625853
frequent words 0.001624551
compact feature 0.0016146250000000002
rare words 0.001612315
training set 0.001611581
known words 0.0016092289999999998
same tag 0.001578341
model 0.001512
following tag 0.001497955
ing segmentation 0.0014792100000000001
tagging sequence 0.001459858
tag predictions 0.001457802
tagging accuracy 0.00145077
tagging problem 0.0014457760000000002
tag decision 0.001390473
