word features 0.00336867
different word 0.00322837
english word 0.002857055
word form 0.002840852
word context 0.002838696
current word 0.002801989
target word 0.002784638
word forms 0.002763217
word lemmatisation 0.00269348
word transformations 0.002628457
regular word 0.002621169
word string 0.002616686
word neveˇdeˇl 0.00258575
feature set 0.002211878
unseen words 0.001860133
pos language 0.0018532090000000002
unknown words 0.001850608
infrequent words 0.001818369
irregular words 0.001807199
frequent words 0.001803953
pos tag 0.001803045
surrounding words 0.001790144
feature sets 0.0017812129999999998
pos information 0.0016618100000000001
morphological types 0.001618195
tag set 0.001605671
label set 0.001565146
morphological paradigm 0.001555545
words 0.00155456
morphological dictionaries 0.001553888
morphological complexity 0.001535513
context features 0.0014897859999999999
pos tagging 0.00148955
same label 0.001481679
pos labels 0.001478643
feature 0.00146683
language corpora 0.001406843
pos tags 0.0013960140000000001
training set 0.001391053
only features 0.0013790249999999999
contextual features 0.001331426
classification model 0.001301827
same system 0.001297038
english set 0.001243313
training corpus 0.001222019
specific language 0.001212544
context information 0.001199294
such labels 0.001192675
joint model 0.001192219
language line 0.0011903410000000001
other systems 0.001189904
pos acc 0.001184463
tagging system 0.0011825849999999999
dicted pos 0.001169961
pipeline model 0.0011594069999999999
same corpora 0.001157637
ing set 0.0011504290000000001
language indepen 0.001138312
morphosyntactic label 0.001134597
label sets 0.0011344810000000001
different morpho 0.001132151
different sources 0.001120532
other methods 0.001113372
set size 0.001099505
speech tag 0.001093633
logical information 0.001084377
single label 0.001080265
other transformation 0.00107426
generic label 0.001073166
wide set 0.001068416
tagging task 0.001053139
label encod 0.001048037
label generalises 0.001048037
specialized label 0.001048037
many languages 0.001046842
contextual information 0.0010409339999999999
set induction 0.001031138
set con 0.0010276740000000001
lemma suffix 0.001026947
features 0.00100988
same time 0.0010026079999999999
relative error 9.948000000000001E-4
other encodings 9.78034E-4
rich languages 9.627519999999999E-4
error reduction 9.516290000000001E-4
information retrieval 9.4847E-4
model 9.31944E-4
training pairs 9.317479999999999E-4
novel approach 9.26031E-4
such dictionaries 9.12732E-4
language 9.10787E-4
general approach 9.00766E-4
lemma prefix 9.004690000000001E-4
european languages 8.92851E-4
semitic languages 8.92828E-4
class labels 8.9035E-4
representative languages 8.90228E-4
current systems 8.83039E-4
annotated corpus 8.741020000000001E-4
accuracy scores 8.74084E-4
