pos tag 0.002362098
pos tags 0.0020613109999999997
probability model 0.00204565
pos tagger 0.00200287
correct pos 0.001967758
pos tagging 0.001928946
parsing models 0.0018842140000000002
lexicalized model 0.001879645
simple model 0.001869419
different word 0.0018210359999999998
sis model 0.001806817
possible word 0.0017819189999999999
detailed model 0.0017771010000000001
pos taggers 0.001743548
parsing algorithm 0.001713213
advanced pos 0.001701097
genuine pos 0.001698085
complementizer pos 0.001698085
parsing results 0.0016695170000000001
probabilistic parsing 0.00165587
german word 0.001649035
standard rules 0.001625683
parsing system 0.001616463
unlexicalized parsing 0.001601327
word order 0.0015692089999999998
parsing errors 0.0015352410000000001
other rule 0.001509766
model 0.00149916
parsing research 0.0014945840000000002
future parsing 0.0014859900000000002
man parsing 0.0014775250000000001
statistical parsing 0.001473831
unlexicalized parser 0.001426215
pure parsing 0.0014210820000000002
cyk parsing 0.0014163650000000002
icalized parsing 0.0014140280000000001
additional word 0.001403337
unknown word 0.0013733999999999999
markov rules 0.001360293
treebank grammar 0.001359883
lexical data 0.001336367
full parser 0.0013319200000000001
flexible word 0.00127773
word generation 0.001273266
word orders 0.001265465
pler word 0.001255041
such results 0.001239363
ing data 0.001233054
normal rules 0.001212199
markov rule 0.00120575
high performance 0.001174313
unlexicalized grammar 0.00117401
binarized rules 0.001172395
parsing 0.00117101
suffix analysis 0.001170893
cfg rules 0.001167689
other languages 0.001155969
treebank corpus 0.001155573
different approaches 0.001146857
error analysis 0.001145353
relative performance 0.001143529
unlexicalized models 0.001143521
different smoothing 0.001140089
second set 0.0011294489999999998
syntactic categories 0.001122807
grammar constraints 0.00111958
sbar category 0.001102416
unknown words 0.001101775
rule lhs 0.001100218
different meaning 0.001092518
german negra 0.00108012
second sentence 0.0010764709999999999
first set 0.00107343
rule type 0.001070457
different choices 0.001062393
negra treebank 0.001058825
language modelling 0.0010528640000000001
such transformation 0.001048913
sparse data 0.00104436
test set 0.00103776
rule types 0.001035164
main clauses 0.0010310979999999998
ing algorithm 0.0010308890000000001
same parent 0.001024508
german newspaper 0.0010211
first sentence 0.001020452
possible contexts 0.001016537
possible paths 0.001016537
possible areas 0.001016537
data problems 0.001007276
above rule 0.0010070300000000001
data the 0.0010057970000000001
various treebank 0.001000621
order markov 0.001000283
parser 9.95898E-4
testing data 9.92511E-4
other means 9.90835E-4
known words 9.88402E-4
ing results 9.87193E-4
infrequent words 9.84655E-4
