word probability 0.0035255860000000003
word distribution 0.003445795
different character 0.0034306500000000004
word types 0.003306545
word clusters 0.003277322
empirical word 0.0032587090000000003
word cluster 0.003239828
vocabulary word 0.003210302
word probabilities 0.003206707
word embeddings 0.0032040880000000003
word man 0.003153875
word distri 0.0031394360000000002
sage word 0.003139083
same character 0.002987111
character persona 0.002857742
character types 0.002812115
character clustering 0.002802782
character type 0.0027728370000000002
latent character 0.002750734
character inference 0.002727801
antecedent character 0.002726624
character entity 0.002705427
character pos 0.002702866
character resem 0.0026833
austen character 0.00267931
third character 0.002677156
inferring character 0.002650984
character mention 0.002643988
character entities 0.002643988
lated character 0.002643988
distractor character 0.002643988
language model 0.002510185
character 0.00240149
persona model 0.002220122
effects model 0.00215986
bayesian model 0.002130576
regression model 0.002124935
guage model 0.002028789
graphical model 0.002026754
model hypothesis 0.0020264510000000003
referential model 0.002019865
sion model 0.002008937
sage model 0.002007033
trained model 0.002006545
formalist model 0.002005957
model 0.00176387
similar words 0.001734575
trigger words 0.001654615
different models 0.001623248
other characters 0.001479634
different effects 0.00142515
training data 0.001421784
such class 0.001379967
words 0.00137265
different author 0.0013687390000000001
language models 0.001340403
different assumptions 0.001323965
different authors 0.001322429
different hypothesis 0.0012917410000000001
different initializations 0.001282993
different kinds 0.0012823370000000001
different topics 0.001276063
different granularities 0.001274388
different choices 0.0012722920000000002
other models 0.001257859
same data 0.001219328
other features 0.001200562
many feature 0.0012002
similar characters 0.001177788
ing characters 0.001159664
ocr errors 0.001149057
same number 0.001145147
initial characters 0.001112158
such effects 0.001108123
major characters 0.001084569
language modeling 0.001076344
same persona 0.001041873
nlp models 0.001014444
tag phrases 0.0010038019999999998
sampling probability 0.001002191
little data 0.001000649
multiple models 9.87717E-4
test case 9.81482E-4
other authors 9.570399999999999E-4
bayesian approach 9.569979999999999E-4
standard nlp 9.55097E-4
feature weights 9.52921E-4
previous work 9.39849E-4
common ocr 9.3541E-4
intermediate class 9.33596E-4
hypothesis class 9.30415E-4
same cluster 9.29529E-4
same author 9.252E-4
time axis 9.21806E-4
background distribution 9.202590000000001E-4
other factors 9.173849999999999E-4
difficult class 9.165499999999999E-4
string representation 9.16325E-4
hierarchical models 9.161519999999999E-4
class hierar 9.09702E-4
