unknown word 0.0041113
unknown words 0.00370007
word length 0.003086768
word segmentation 0.003078521
word boundaries 0.003072853
word problem 0.003047248
word candidate 0.003023374
word detection 0.003001644
word extraction 0.0029677700000000002
new word 0.002965687
word boundary 0.002961795
correct word 0.002960986
typical word 0.002924019
foreign word 0.002923911
known word 0.002920171
word analyzer 0.002901786
word seg 0.002898767
word candidates 0.002892682
word abcd 0.002884711
word segmenta 0.002881369
word occurrences 0.002880843
english words 0.0027768420000000003
different words 0.002728625
new words 0.0025544570000000004
foreign words 0.002512681
known words 0.002508941
words usu 0.0024694260000000003
unusual words 0.0024694260000000003
written words 0.0024694260000000003
words 0.00216815
unknown string 0.002052471
unknown positions 0.00192936
unknown segments 0.001927575
unknown segment 0.001851898
unknown seg 0.001851307
unknown lexicons 0.001838932
statistical model 0.001802386
unknown 0.00153192
pos tags 0.001455451
chinese text 0.001396091
large corpus 0.001346576
statistical analysis 0.001338958
morphological analysis 0.001334896
identification approach 0.001333395
merging approach 0.001276656
other thai 0.001268749
few characters 0.001231757
other string 0.001228627
approach freq 0.001225588
other languages 0.001224204
sign approach 0.00122039
statistical rule 0.001219642
information technology 0.001217871
individual characters 0.001211815
textual information 0.001201578
thai language 0.001200779
contextual information 0.0011987159999999998
available information 0.0011940689999999999
data set 0.0011897980000000002
character sequence 0.001187176
information agent 0.001183281
pos disambiguation 0.001179479
traditional approach 0.001178573
other class 0.001174565
approach none 0.00117277
morphological rules 0.0011723789999999999
tual information 0.001170725
effective approach 0.001169337
joint character 0.001169218
matching algorithm 0.001161045
character association 0.001152085
total number 0.0011459360000000002
dependent characters 0.001141718
ent characters 0.001137435
leni characters 0.001136134
tonal characters 0.001136134
ual characters 0.001136134
english languages 0.00112482
string matching 0.001116536
following string 0.0011134510000000001
text string 0.001100139
model 0.00109843
thai dictionary 0.0010838549999999999
rule set 0.0010820550000000002
accuracy results 0.001066803
frequency distribution 0.001066058
language nlp 0.001064734
segmentation algorithm 0.001064201
other lan 0.001051232
thai lexicon 0.001046909
statistical pattern 0.001036957
natural language 0.001030177
identification accuracy 0.001026377
japanese texts 0.001023749
morphological analyzer 0.0010222999999999999
same set 0.001017205
other hand 0.001011221
few english 0.001010406
cal analysis 9.93947E-4
following segments 9.885550000000001E-4
