word clustering 0.003106687
word clusters 0.00298362
single word 0.002796534
word size 0.002712699
word boundary 0.002576728
word pairs 0.002545472
word indexing 0.002538968
word pair 0.002534083
word boundaries 0.002528715
other words 0.002494634
new words 0.002433856
function words 0.002231624
arabic words 0.0022067700000000003
similar words 0.002150272
results data 0.002112002
yields words 0.002066192
inflected words 0.0019874660000000002
first data 0.001894827
different root 0.001839168
different roots 0.001820617
arabic data 0.00178425
data set 0.0017646570000000002
words 0.00172907
clustering algorithm 0.001728033
evaluation data 0.001672758
second data 0.001670051
data sets 0.0016464280000000001
problematic data 0.001620078
third data 0.001614186
fifth data 0.001558065
sizeable data 0.001553658
data description 0.001553658
different affixes 0.0015057039999999999
different domains 0.0014472069999999998
algorithm table 0.001358423
algorithm test 0.001346789
same root 0.001281088
results table 0.001260789
test results 0.001249155
correct clustering 0.0012435760000000001
classification algorithm 0.001227576
current results 0.001212956
morphological knowledge 0.00119768
large corpus 0.0011807060000000001
based clustering 0.001177228
morphological similarity 0.0011733899999999998
algorithm limitations 0.00116819
perfect clustering 0.001165016
algorithm illustrated 0.001155553
algorithm deals 0.001151923
single text 0.001151174
algorithm adamson 0.001150569
the algorithm 0.001150569
root letter 0.001137268
successful clustering 0.0011329550000000002
correct clusters 0.001120509
arabic text 0.00111408
cluster size 0.001112486
correct cluster 0.0011001560000000001
link clustering 0.001099231
root dictionaries 0.001096489
accurate clustering 0.001082184
size root 0.001080357
root size 0.001080357
other hand 0.001078893
lexical resources 0.001075966
new evaluation 0.001070994
manual clusters 0.0010668589999999999
new candidate 0.001064174
acceptable results 0.001056566
based clusters 0.001054161
weak root 0.001048318
first set 0.001046384
cluster distribution 0.001046254
root lexicon 0.001038743
information retrieval 0.001029491
other variations 0.001023595
root candidates 0.001020868
cluster quality 0.001019589
benchmark clusters 0.001011079
morphological variation 0.001001292
morphological similarities 9.81548E-4
morphological relatedness 9.81548E-4
morphological frugality 9.81548E-4
exact clusters 9.70629E-4
inflectional language 9.62974E-4
position cluster 9.560009999999999E-4
cluster item 9.48174E-4
such approaches 9.440900000000001E-4
accurate cluster 9.38764E-4
cluster formation 9.34926E-4
independent roots 9.33164E-4
root consonants 9.273160000000001E-4
arabic test 9.21403E-4
root wqf 9.19449E-4
root qwm 9.170160000000001E-4
root indexing 9.06626E-4
free text 9.04141E-4
algorithm 9.03086E-4
root identification 9.02216E-4
