pos tag 0.002753176
other words 0.0026599600000000003
pos tags 0.002578575
english words 0.002541016
class words 0.002539542
similar words 0.0025341210000000003
same pos 0.002526978
word clustering 0.002526969
distributional pos 0.002504558
many words 0.002475227
bengali words 0.0024738750000000004
root words 0.00237798
english word 0.002366826
pos lexicon 0.0023546110000000004
seed words 0.0023543130000000002
english pos 0.002335686
labeled words 0.002331594
similar pos 0.002328791
unsupervised word 0.002314212
frequent words 0.0023051240000000004
unlabeled words 0.002295703
distinct words 0.002287821
unsupervised pos 0.002283072
reliable words 0.002277832
rare words 0.00227637
beled words 0.0022719600000000004
unreliable words 0.002265881
capitalized words 0.0022648370000000004
informative words 0.0022648370000000004
pos tagging 0.002258266
target word 0.002240251
word type 0.002237419
possible pos 0.002229598
pos identification 0.002222651
word order 0.002215917
morphological information 0.00220718
pos induction 0.0021875600000000003
previous pos 0.002186583
corresponding word 0.0021809209999999997
common word 0.002173907
labeled word 0.002157404
word types 0.00212686
unlabeled word 0.002121513
word segmentation 0.00211474
word sense 0.002106087
accurate word 0.002096522
fixed word 0.002092269
free word 0.0020915639999999997
word combin 0.002090584
pos tagsets 0.002066435
pervised pos 0.002060222
pos induc 0.00205997
words 0.00200377
morphological features 0.00199087
morphological clustering 0.001899849
morphological cluster 0.001827429
distributional information 0.0017108380000000001
morphological knowledge 0.00154658
morphological infor 0.00153979
clustering algorithm 0.001532522
morphological parsers 0.0015059140000000001
learning algorithm 0.0015044759999999998
distributional features 0.0014945280000000002
morphological analyzer 0.00149179
morphological similarity 0.001472945
morphological analyzers 0.001464092
same set 0.001447893
training set 0.001408567
english corpus 0.001400723
bengali corpus 0.001333582
distributional cluster 0.001331087
sufficient information 0.001329785
distributional approach 0.001329458
wsj corpus 0.001319792
test data 0.001290092
logical information 0.001284891
corpus frequency 0.0012814599999999999
model 0.00127393
tributional information 0.0012691999999999998
different tags 0.001262503
same number 0.001262246
similar set 0.001249706
other results 0.001239309
test set 0.001233837
assigned tag 0.001233179
tag description 0.00123201
ing algorithm 0.00122526
induction algorithm 0.001224253
other clusters 0.001223725
automatic feature 0.001207198
binary feature 0.001188363
useful feature 0.001158378
treebank tags 0.001156267
such labelings 0.001149821
bootstrapping algorithm 0.0011493599999999999
corpus fre 0.001137944
same problem 0.0011364880000000002
unannotated corpus 0.001136457
algorithm labels 0.001135689
appealing feature 0.001128075
