learning model 0.002346388
model input 0.0023201560000000003
language model 0.002249981
model baseline 0.002097627
model our 0.002030459
our model 0.002030459
model architecture 0.002006342
model design 0.001978427
model architectures 0.0019400790000000002
semantic models 0.0019378479999999998
elaborate model 0.001935167
skipgram model 0.0019346480000000002
model updates 0.0019346480000000002
model combines 0.0019346480000000002
model moderates 0.0019346480000000002
model 0.00175843
feature word 0.001697642
such models 0.001688583
learning models 0.001610058
semantic representations 0.001554326
word learning 0.001516162
language models 0.001513651
human word 0.001450115
perceptual data 0.00143157
perceptual feature 0.001412702
training data 0.0014050450000000002
such concepts 0.0013741500000000002
linguistic representations 0.0013403809999999999
semantic properties 0.001336832
linguistic information 0.001331075
concept words 0.001316884
previous models 0.00130928
such information 0.001295755
perceptual representations 0.001281842
esp models 0.001279248
different concept 0.001274612
perceptual information 0.001272536
representations information 0.00126785
vector representations 0.00126656
linguistic input 0.001263529
concept learning 0.001262325
feature vectors 0.001253517
same data 0.001235838
guage models 0.001232931
perceptual learning 0.0012312220000000001
native models 0.001227115
modal models 0.0012268539999999999
context word 0.001212059
perceptual input 0.00120499
semantic category 0.001203373
other concept 0.001198952
noun concepts 0.001197195
semantic rep 0.001197137
semantic represen 0.001186704
linguistic vectors 0.001185882
training input 0.001178465
other words 0.0011671020000000002
noun concept 0.001163895
concept pairs 0.001161717
corpus perceptual 0.001157708
word type 0.00115678
target word 0.001153997
concepts method 0.0011488800000000001
perceptual features 0.00114752
ture word 0.001141947
semantic memory 0.0011417369999999999
training corpus 0.001131183
perceptual vectors 0.001127343
semantic nlp 0.001111896
training pairs 0.001104089
concrete concepts 0.001095151
abstract concepts 0.001086601
language learning 0.001079509
method vector 0.001069195
perceptual representation 0.001062233
concrete concept 0.001061851
verbs concept 0.0010572140000000001
parameter vector 0.001038937
many concepts 0.001037318
concrete words 0.001030001
concrete representations 0.001026062
models 0.0010221
abstract representations 0.001017512
human language 0.0010134620000000001
sparse feature 0.00101326
ing representations 0.001012109
representation learning 0.001006927
related concepts 0.001005325
various concept 0.0010045100000000001
ing information 0.001002803
cslb data 0.001001681
usf data 0.001000204
tual feature 9.99479E-4
feature bag 9.81377E-4
linguistic represen 9.727589999999999E-4
linguistic signal 9.603039999999999E-4
feature strength 9.51882E-4
resentation feature 9.46075E-4
concept types 9.384700000000001E-4
ing input 9.352570000000001E-4
