word segmentation 0.00300428
chinese word 0.002570611
new word 0.00243693
word length 0.002312912
word boundary 0.002284864
current word 0.002251627
word segmenter 0.002242331
whole word 0.002218831
word definition 0.002194553
stop word 0.00218302
word list 0.002179523
novel word 0.002168377
rate word 0.0021543400000000002
treated word 0.002145184
word segmenta 0.002144272
word identification 0.0021427440000000002
different segmentation 0.002071202
different features 0.002003952
segmentation method 0.001989084
feature corpus 0.00195622
different corpus 0.001803542
other segmentation 0.0017401959999999998
training corpus 0.001740166
segmentation algorithm 0.001736599
segmentation problem 0.001705836
feature vector 0.001666915
chinese words 0.00165204
segmentation approach 0.001603609
algorithm words 0.001601168
segmentation ambiguity 0.001587564
segmentation results 0.00157898
segmentation performance 0.0015774679999999998
retrieval model 0.0015677680000000002
segmentation class 0.001537915
svm model 0.001536113
chinese character 0.00153214
feature space 0.0015230679999999998
ranking model 0.001521896
segmentation approaches 0.001520025
segmentation methods 0.00151876
new words 0.001518359
various segmentation 0.001508461
dictionary feature 0.001503202
chinese information 0.0014993200000000002
training sentence 0.001487735
segmentation accuracy 0.001485887
segmentation result 0.0014750269999999998
probability information 0.0014708120000000002
segmentation task 0.001466305
segmentation systems 0.001458216
other information 0.001452045
segmentation decision 0.001449995
mrf model 0.001442086
segmentation algorithms 0.001438815
segmentation evaluation 0.001437292
based segmentation 0.00143053
segmentation scheme 0.001426366
statistical features 0.001417041
effective feature 0.001415819
character string 0.0014067060000000002
feature vectors 0.0014040839999999999
traditional segmentation 0.001399986
segmentation granularity 0.001396063
granularity segmentation 0.001396063
dts feature 0.0013909209999999998
character sequence 0.001390241
different length 0.001379834
match segmentation 0.001374127
segmentation prob 0.0013651779999999999
segmentation meth 0.001362042
test corpus 0.001359184
segmentation granularities 0.001358779
segmentation deci 0.001356185
ictclas segmentation 0.001356185
treat segmentation 0.001356185
definite segmentation 0.001356185
large corpus 0.0013460730000000001
method performance 0.001345412
different seg 0.001345307
above features 0.001327879
different size 0.0013133350000000001
words boundaries 0.001306872
different statistics 0.001292433
scribe features 0.00129039
character pairs 0.00128393
different rank 0.001273641
chinese sentence 0.00126738
character tagging 0.0012644280000000002
different labels 0.001252963
corpus number 0.001252613
size training 0.0012499590000000001
different stop 0.001249942
different queries 0.001248174
different granularity 0.001246125
pound words 0.001237329
small training 0.001230189
unknown words 0.001224169
web corpus 0.001219803
method map 0.00121958
sentence algorithm 0.0012165079999999998
