word segmentation 0.00538537
word probability 0.005334722
chinese word 0.005225116
new word 0.005184459
sentiment word 0.005095966
word set 0.005003528
seed word 0.00497807
candidate word 0.0049320119999999995
word pair 0.004913804
single word 0.004901277
left word 0.004901119
word expression 0.004897745
current word 0.00488725
word detection 0.004850119
acter word 0.004842186
word seg 0.004831208
auxiliary word 0.004827473
word segmen 0.004825892
adverbial word 0.00482582
date word 0.004822656
word benefits 0.004822496
word extrac 0.004821733
word probabili 0.004821265
word detec 0.004821265
word setwc 0.004821265
such words 0.002936635
chinese words 0.0028919059999999996
new words 0.0028512489999999997
sentiment words 0.002762756
seed words 0.0026448599999999997
positive words 0.0026245739999999997
negative words 0.0025886019999999997
frequent words 0.0025702299999999997
single words 0.002568067
target words 0.0025615919999999997
auxiliary words 0.002494263
adverbial words 0.0024926099999999997
neighboring words 0.002490484
extract words 0.0024884399999999997
words 0.00226095
first model 0.001963303
markov model 0.001698505
association model 0.0016719019999999999
joint model 0.001631736
model particles 0.0015822129999999998
training data 0.001456068
model 0.00135477
segmentation algorithm 0.001319638
translation polarity 0.001127176
segmentation errors 0.001092866
new sentiment 0.001092105
conditional probability 0.001087305
english translation 0.001076188
own language 0.0010696619999999999
high probability 0.0010512499999999999
language processing 0.001049744
segmentation tool 0.001038799
natural language 0.001037873
behavior data 0.001036408
data preparation 0.001033114
czech data 0.001033114
input method 0.001026405
language styles 0.001021362
such measures 0.001012911
probabilistic models 0.0010108
algorithm input 0.001009781
single character 9.83198E-4
classification models 9.82906E-4
different measures 9.60114E-4
mutual information 9.564249999999999E-4
work new 9.49084E-4
corpus statistics 9.431019999999999E-4
different measure 9.31831E-4
such studies 9.26978E-4
good results 9.26732E-4
first measure 9.17476E-4
machine translation 9.15065E-4
sification models 9.13265E-4
typical models 9.115060000000001E-4
different settings 9.10684E-4
chinese char 9.059770000000001E-4
sentiment phrase 9.0499E-4
linguistic features 9.027760000000001E-4
other languages 9.015010000000001E-4
other measures 8.99551E-4
sentiment analysis 8.985600000000001E-4
chinese nlp 8.95257E-4
ratio test 8.941239999999999E-4
first genre 8.74975E-4
baselines first 8.69331E-4
chinese pinyin 8.62725E-4
dynamic time 8.61045E-4
sogou chinese 8.609620000000001E-4
information entropy 8.59544E-4
undesirable results 8.3865E-4
tio test 8.26293E-4
new wordsw 8.241209999999999E-4
comparative results 8.20537E-4
timal results 8.15354E-4
results whenk 8.15354E-4
