many words 0.002683317
different word 0.002683233
same word 0.002664288
lexicon words 0.002636169
word clusters 0.0025926630000000003
frequency words 0.002557954
word cluster 0.002554017
few words 0.002509082
word class 0.002493594
target words 0.002407799
target word 0.002401349
words table 0.002388871
only words 0.002386977
frequent words 0.002386758
word forms 0.002385
oov words 0.0023745759999999998
word coverage 0.002371102
word classes 0.00234767
corresponding words 0.002343883
ambiguous words 0.002333845
unknown words 0.00233323
feature words 0.002322331
known words 0.0023217389999999997
word sets 0.002294219
unseen words 0.002292041
closed word 0.002290887
rare words 0.002289188
open word 0.0022847230000000002
separate word 0.002284599
word trigrams 0.002280109
word graphs 0.002280109
words 0.0020688
pos information 0.001497969
same text 0.001395531
graph model 0.001377574
other clusters 0.001333055
tagger model 0.0012929830000000002
english corpus 0.001270684
unsupervised pos 0.001224923
other way 0.0012085569999999999
unsupervised method 0.00120129
pos tagger 0.001176152
different tags 0.001159508
class information 0.001158661
clustering algorithm 0.001145597
tma model 0.001141109
small corpus 0.001139031
other models 0.001136877
markov model 0.00112915
national corpus 0.00112474
pos tagging 0.001124341
trigram model 0.001119191
other parameters 0.00111189
model deals 0.0011060100000000002
text coverage 0.001102345
web corpus 0.001101328
same cluster 0.001093605
corpus coverage 0.0010872
pos corpora 0.001083414
other partitioning 0.001063581
other languages 0.001052632
context vector 0.001051436
semantic class 0.0010371949999999999
other works 0.001027746
viterbi pos 0.001027726
newspaper corpus 0.001025719
monolingual text 0.001018165
unstructured text 0.00101286
text bar 0.00101286
unlabeled corpus 0.001002976
syntactic category 9.96065E-4
mutual information 9.86229E-4
category distribution 9.81974E-4
lexicon probability 9.81248E-4
graph clustering 9.645489999999999E-4
different techniques 9.58965E-4
lexicon performance 9.57255E-4
large clusters 9.52047E-4
possible tag 9.502639999999999E-4
high frequency 9.31273E-4
efficient algorithm 9.275970000000001E-4
different evaluation 9.26342E-4
tag set 9.17416E-4
graph representation 9.089479999999999E-4
low number 9.073759999999999E-4
possible tags 9.020110000000001E-4
syntactic clusters 8.96809E-4
appropriate category 8.939039999999999E-4
clustering methods 8.93094E-4
many edges 8.91977E-4
standard tags 8.89492E-4
model 8.87383E-4
lexicon size 8.83307E-4
various tag 8.79688E-4
many neighbours 8.784509999999999E-4
different languages 8.70773E-4
optimal number 8.6469E-4
many languages 8.64407E-4
low frequency 8.60754E-4
tag perplexity 8.54273E-4
