language model 0.0030339
word tokens 0.0028394740000000003
previous word 0.002814177
single word 0.002798864
word type 0.002750072
syriac word 0.002741497
next word 0.002728439
baseline model 0.002726985
example word 0.002724779
unknown word 0.00269511
joint model 0.002672426
segmentation model 0.002669796
known word 0.002638086
hybrid word 0.002636533
word ܢŵƅƅƈɗɔ 0.00261112
word transliteration 0.002610222
word types 0.002607014
word distributions 0.0026018260000000002
vious word 0.002598878
morphological segmentation 0.002533016
separate model 0.002396662
morphological tags 0.002374096
model results 0.002340943
morphological information 0.002317848
morphological tagging 0.002315422
pipeline model 0.002309329
individual model 0.002298471
tion model 0.002282579
gender model 0.002273219
morphological analysis 0.002269095
model con 0.002252829
hybrid model 0.002219793
model hybrid 0.002219793
syromorph model 0.002211679
markov model 0.002207302
combined model 0.002203331
model total 0.002199557
mentation model 0.002199237
model our 0.002196681
model maxent 0.002187635
omarkov model 0.002186263
fette model 0.002183579
morphological analyzer 0.002171117
morphological tagger 0.002168652
morphological attributes 0.002123197
morphological disambiguation 0.00210098
morphological annotation 0.002098189
morphological attribute 0.002091058
morphological analyzers 0.002056676
morphological ana 0.002050572
morphological disambigua 0.002045577
morphological annota 0.002044312
model 0.00195342
other words 0.0017947450000000002
other language 0.001711845
data baseline 0.001669815
training data 0.00154651
pos tag 0.0015145459999999999
joint baseline 0.001492571
segmented words 0.001489646
unknown words 0.0014883300000000002
stem tag 0.0014570310000000001
semitic words 0.001434757
known words 0.001431306
unlabeled words 0.001414485
trigram language 0.001414378
frequent words 0.001411518
additional language 0.001394692
rare words 0.0013928130000000001
other stem 0.001390353
feature set 0.001388231
pos tags 0.0013739590000000001
cal language 0.001360946
semitic language 0.001351857
inflected language 0.001349675
language tools 0.0013469649999999999
stem case 0.001345729
lack language 0.001344235
joint accuracy 0.001333294
other models 0.0013287300000000002
stem tags 0.001316444
pos tagging 0.001315285
tag accuracy 0.001312331
joint approach 0.00131062
further feature 0.001282327
stem tagging 0.00125777
baseline root 0.0012455090000000001
possible context 0.001245037
different models 0.001230547
segmented data 0.001222516
token segmentation 0.001214582
previous stem 0.001203005
suffix tag 0.001196684
joint task 0.001178666
pos tagger 0.001168515
correct stem 0.001168265
words 0.00116338
baseline results 0.001161088
labeled data 0.0011604760000000001
data sparsity 0.001151892
