clustering model 0.003336876
tokens model 0.003195462
character model 0.003088482
english model 0.003050656
entropy model 0.003005521
bayesian model 0.0029914440000000002
vector word 0.002978845
final model 0.002950058
second model 0.002944276
probabilistic model 0.002918073
morphology model 0.002910031
sequence model 0.002909694
linear model 0.002897494
ddcrp model 0.002888423
mixture model 0.0028639390000000002
generative model 0.002845772
full model 0.00283212
model behavior 0.002818256
model flexibility 0.002817762
english word 0.002751696
word classes 0.002720945
main word 0.00271834
word type 0.002645876
word embeddings 0.002608892
word types 0.002605791
model 0.00255448
polyglot word 0.002526335
ith word 0.002512019
word clusterings 0.002504512
frequent words 0.001964271
few words 0.001906594
rare words 0.0018226829999999999
jth words 0.00177944
words 0.00152934
morphological features 0.001440986
unsupervised pos 0.001425067
english pos 0.001382916
corpus statistics 0.0013822700000000001
prior distribution 0.00136382
data point 0.001341097
cluster parameters 0.0013126470000000001
pos tagging 0.0013050050000000001
pos induction 0.001282001
previous results 0.001281149
experiments data 0.001261605
different number 0.001248252
distributional features 0.0012263
similar results 0.001192508
new cluster 0.001186772
same table 0.0011851040000000002
same number 0.001180924
distributional information 0.001162573
gaussian cluster 0.001158689
pos clus 0.00115234
data dimensionality 0.001151865
data points 0.00115118
pos induc 0.001145182
morphological classes 0.001144987
pos labels 0.001143234
morphological structure 0.0011377
ddcrp models 0.001132118
standard clusters 0.001124713
same level 0.0011220050000000001
morphological segmentation 0.001117176
cluster assignment 0.0011026579999999999
cluster assignments 0.001086894
feature weights 0.001074254
different sizes 0.0010687539999999999
cluster centroid 0.001067419
continuous vector 0.001052333
parametric models 0.001051655
arbitrary features 0.001049513
tag dictionary 0.001044337
first sampling 0.001040036
morphological fea 0.00103456
corpus 0.00103199
different lan 0.001031414
morphological similarity 0.001030239
different priors 0.001028023
logical features 0.001024528
previous work 0.0010196509999999999
similar size 0.001016924
vector represen 0.001014527
other scores 0.001013895
tributional features 0.001013492
different domains 0.0010134620000000001
different parametrizations 0.0010134620000000001
other languages 0.00100798
likelihood function 0.001004573
gibbs sampler 9.98963E-4
many tags 9.96516E-4
many languages 9.89689E-4
information source 9.831430000000001E-4
similarity function 9.81893E-4
morphological rules 9.73943E-4
wikipedia tokens 9.535310000000001E-4
morphological paradigms 9.3625E-4
fine tokens 9.321830000000001E-4
coarse tokens 9.31536E-4
tokens coarse 9.31536E-4
