human evaluation 0.00479017
evaluation metric 0.00444648
evaluation metrics 0.00443629
translation evaluation 0.00439795
evaluation score 0.0040297300000000005
automatic evaluation 0.00399644
evaluation scores 0.003886199
evaluation framework 0.003643009
summarization evaluation 0.003603588
ratio evaluation 0.003552296
evaluation variation 0.0035388
fluency evaluation 0.003537305
evaluation guideline 0.003508292
summary evaluation 0.003481962
evaluation methods 0.003478342
adequacy evaluation 0.0034575920000000002
various evaluation 0.00345686
evaluation task 0.003420738
evaluation tides 0.003387961
evaluation guidelines 0.003382059
final evaluation 0.003373814
evaluation performance 0.003364025
evaluation coverage 0.003356649
coverage evaluation 0.003356649
evaluation perspective 0.003344414
evaluation package 0.003325004
evaluation plane 0.0033232540000000003
evaluation duc 0.003321995
evaluation examples 0.003320905
correctness evaluation 0.003316252
evaluation bottleneck 0.003314501
evaluation 0.00294793
automatic metric 0.00254706
translation sentence 0.00245955
human evaluations 0.002415991
human guideline 0.002402602
human summary 0.002376272
such metrics 0.002265225
human judgment 0.002264727
human assessor 0.002223976
human assessors 0.002213936
human judge 0.002213154
human evaluator 0.002209059
bleu metric 0.002198857
metric family 0.002075517
single metric 0.002062949
particular metric 0.002057246
machine translation 0.001967821
rouge metric 0.001900103
metric aev 0.001889717
metrics aev 0.001879527
metric families 0.001877602
reference translations 0.001830458
translation community 0.0018285250000000001
proposed translation 0.001821453
bleu score 0.0017821069999999998
other system 0.001723952
automatic summarization 0.0017041679999999998
precision score 0.00169324
bleu scores 0.001638576
recall score 0.001590222
reference summaries 0.0015857129999999999
score formula 0.001571398
precision scores 0.001549709
automatic method 0.001531401
available data 0.001528365
fluency scores 0.0015276439999999999
available reference 0.001522187
different aspects 0.001521535
metric 0.00149855
coverage score 0.001490519
metrics 0.00148836
different criteria 0.001480643
automatic question 0.001476002
reference answer 0.001470081
answer set 0.001465403
translation 0.00145002
adequacy scores 0.001447931
recall scores 0.001446691
different members 0.001428372
data points 0.0014218120000000002
automatic paraphrasing 0.0014148529999999998
original sentence 0.001407614
axis reference 0.001399358
similar value 0.001381134
reference summary 0.00137945
system unit 0.001376704
test sentences 0.001373504
system performance 0.001356334
extraneous words 0.001352516
current reference 0.001345571
set candidates 0.0013326219999999999
same family 0.001327145
set references 0.001318905
test sets 0.001310097
reference unit 0.001281883
individual reference 0.001278041
other nlp 0.001244282
test corpora 0.00123933
single number 0.001236989
