word context 0.0037658989999999996
word similarity 0.0036849359999999998
oov word 0.003333942
candidate word 0.0033328589999999996
same word 0.003316869
word form 0.003178941
word detection 0.003147689
word distribution 0.003141151
word type 0.0030924639999999996
target word 0.003079705
word identification 0.0030727159999999996
word distri 0.003050612
word definition 0.0030418209999999997
formed word 0.0030237349999999996
ical word 0.0030192749999999997
word lookin 0.0030166639999999996
word whitelist 0.0030166639999999996
word detector 0.0030166639999999996
word flm 0.0030166639999999996
context words 0.002246999
different text 0.0020021179999999998
oov words 0.0018150419999999998
other text 0.00181243
text normalisation 0.0017774700000000002
context features 0.00175166
similarity features 0.001670697
different features 0.0016520089999999999
lexical normalisation 0.001590353
english text 0.0015727850000000002
target words 0.001560805
language model 0.001539504
normalisation model 0.001529779
text tokens 0.0015283290000000001
formed words 0.001504835
corpus data 0.001500633
feature model 0.001485337
sms text 0.001465509
different feature 0.0014462659999999999
text processing 0.0014456920000000002
text type 0.001428334
text messages 0.001417982
text types 0.0014138010000000001
text generation 0.001395534
input text 0.0013939500000000001
short text 0.001391698
lexical edit 0.0013797610000000002
text support 0.001377976
text modelling 0.00137517
text mining 0.001370247
newswire text 0.0013570470000000001
text mes 0.001355276
text normalisa 0.001354724
training data 0.001352834
text genres 0.001352798
context tokens 0.001341218
model score 0.0013308
error model 0.001329923
lexical form 0.001327694
local context 0.001323206
noisy context 0.0013230730000000001
twitter data 0.0013221790000000001
words 0.00128967
context window 0.0012867220000000001
frequency features 0.0012842180000000002
different task 0.001267865
lexical forms 0.001250349
lexical variation 0.001237898
following features 0.001223331
different threshold 0.001219352
sufficient context 0.001214353
useful context 0.0012032520000000001
relative similarity 0.001201578
trigram model 0.001199177
context support 0.0011908650000000002
lexical items 0.0011888
context modelling 0.001188059
context inference 0.001187077
context mod 0.001186184
context windows 0.00118339
lexical normalisa 0.001167607
twitter normalisation 0.001166979
context fit 0.001165803
age context 0.001165803
lexical deviation 0.0011656120000000001
lexical rendering 0.0011656120000000001
lexical normali 0.0011656120000000001
normalisation candidate 0.001157319
channel model 0.00115665
similar features 0.001155472
morphophonemic similarity 0.001145168
such candidate 0.001129252
normalisation method 0.001128967
markov model 0.001126062
standard english 0.0011148
sms data 0.001109299
different sources 0.001085174
different datasets 0.0010775819999999999
ter data 0.001076327
normalisation candidates 0.001071458
different methodologies 0.0010669899999999999
