scf information 0.003047242
scf acquisition 0.002893352
scf lexicon 0.002679931
scf types 0.002564899
scf learning 0.002545482
scf filter 0.002532725
distinct scf 0.002478279
scf candidates 0.002449012
scf builder 0.0024471709999999997
scf candidate 0.002445457
test verbs 0.0017298399999999998
corpus data 0.001721993
other information 0.001690306
different scfs 0.0016412900000000001
syntactic features 0.001559251
frequency information 0.001543454
french verbs 0.001480468
lexical information 0.0014652480000000002
subcategorization information 0.001388575
german verbs 0.001386323
tative verbs 0.001384978
large corpus 0.00135711
input data 0.001345768
subcategorization frames 0.0013186830000000002
syntactic lexicon 0.0013167959999999999
acquisition system 0.001294547
probability frames 0.0012883500000000002
syntactic analysis 0.001275587
distinct scfs 0.001269829
predefined scfs 0.0012685790000000001
correct scfs 0.0012621890000000001
scfs candidates 0.0012405620000000002
intransitive scfs 0.001240519
tentative scfs 0.0012388490000000002
subcategorization acquisition 0.0012346850000000001
acquisition performance 0.00115896
large subcategorization 0.001145591
other cases 0.001142147
verbs 0.00113485
input corpus 0.001123279
first system 0.001120074
sufficient information 0.001110263
other source 0.00110987
statistical hypothesis 0.001104554
other languages 0.001099294
large lexicon 0.001090389
syntactic category 0.001086109
automatic acquisition 0.001085051
experimental evaluation 0.001070662
raw corpus 0.001069136
incorrect frames 0.001068276
predefined frames 0.001060579
tic frames 0.00105352
easy evaluation 0.0010429649999999999
newspaper corpus 0.00104005
previous work 0.00103662
constructs frames 0.001034524
mantic classes 0.001033904
relative frequency 0.0010274989999999999
subcategorization lexicon 0.001021264
lexical dependencies 0.0010175660000000001
direct evaluation 0.001015665
acquisition process 0.001013672
journalistic corpus 0.001009074
following features 0.001007551
previous subcategorization 0.00100716
corpus occurrences 0.0010042060000000001
lexical resources 0.001002139
statistical nlp 9.972890000000002E-4
gold standard 9.946360000000001E-4
large lexicons 9.87918E-4
evaluation measures 9.84565E-4
system precision 9.81879E-4
different versions 9.81859E-4
manual work 9.8161E-4
simple threshold 9.73818E-4
large corpora 9.69807E-4
evaluation cam 9.65539E-4
specific threshold 9.64829E-4
threshold value 9.6144E-4
automatic work 9.56292E-4
evaluation campaign 9.533759999999999E-4
tomatic acquisition 9.446159999999999E-4
natural language 9.43527E-4
varied frequency 9.42424E-4
general language 9.415960000000001E-4
many nlp 9.412660000000001E-4
nlp tasks 9.36962E-4
type recall 9.32373E-4
work experiments 9.32008E-4
general lexicon 9.29955E-4
future work 9.28123E-4
subcategorization lexicons 9.18793E-4
binomial hypothesis 9.010469999999999E-4
large newspaper 8.976559999999999E-4
cambridge system 8.946189999999999E-4
comprehensive subcategorization 8.922390000000001E-4
low probability 8.897940000000001E-4
first experiments 8.862939999999999E-4
system tags 8.829129999999999E-4
