morphological disambiguation 0.002212863
morphological analysis 0.002037806
level tag 0.002030537
morphological information 0.002011644
morphological ambiguity 0.0019960209999999997
morphological features 0.00190467
different disambiguation 0.0018514410000000001
training corpus 0.001840193
pos disambiguation 0.001817288
unknown words 0.0018050750000000002
different tags 0.00172755
previous tag 0.0016939379999999999
category tag 0.0016749159999999998
disambiguation rules 0.001667722
morphological analyser 0.001647354
different methods 0.001616773
morphological disambiguator 0.001611075
morphological nalyser 0.001611009
morphological nalysis 0.001606405
morphological mbiguity 0.001604103
basque language 0.00160066
disambiguation system 0.0015810910000000002
standard words 0.001568737
hmm model 0.0015588210000000002
disambiguation methods 0.0015437580000000001
possible tags 0.001527081
large training 0.001487909
known words 0.001487146
same corpus 0.001461975
cesses words 0.00145564
test corpus 0.0014486619999999999
statistical disambiguation 0.001438896
agglutinative language 0.0014280550000000001
inflected language 0.001410821
level tagging 0.001388769
good disambiguation 0.001380021
linguistic methods 0.001333873
other languages 0.001319536
syntactic analysis 0.001304483
training cor 0.0013016689999999999
level tagset 0.0012888980000000001
small training 0.0012884189999999998
supervised training 0.001282168
pervised training 0.00128209
good results 0.001261847
different interpretations 0.0012487919999999999
first level 0.001248687
disambiguation module 0.00124426
statistical approach 0.0012339690000000001
small corpus 0.0012323920000000001
logical disambiguation 0.001213848
statistical methods 0.001204228
new tags 0.001202439
input text 0.001199278
lemma disambiguation 0.001191374
context methods 0.00119127
last level 0.001190743
standard rules 0.001183486
lexical units 0.001177072
good approach 0.001175094
initial ambiguity 0.001165446
words 0.00116376
stochastic tagger 0.001139406
ambiguity rate 0.0011268839999999999
constraint rules 0.001122343
third level 0.001116493
language 0.00111614
stochastic models 0.001108799
level formalism 0.001101527
high error 0.001100185
pervised learning 0.001093583
second level 0.001086341
accurate rules 0.0010838990000000001
subcategory tags 0.001072267
average number 0.001072085
ambiguity classes 0.001061733
other systems 0.0010510580000000001
possible interpretations 0.0010483229999999999
tic information 0.001045555
other hand 0.001045549
based tagger 0.001045263
possible readings 0.001043108
whole system 0.0010361
following processes 0.001026045
model 0.00102023
following reasons 0.001011523
following criteria 0.00100352
linguistic variants 9.985649999999999E-4
error rate 9.97794E-4
incremental analysis 9.95674E-4
tatoo tagger 9.922120000000001E-4
first order 9.84955E-4
main goal 9.72895E-4
enriched lexicon 9.676730000000001E-4
similar combination 9.64351E-4
training 9.4811E-4
guation methods 9.37899E-4
main reasons 9.33599E-4
agglutinative languages 9.32731E-4
general tagset 9.31891E-4
