single word 0.002483255
source word 0.002343482
language words 0.0021922
same words 0.001573325
language text 0.0015725560000000001
language collocations 0.001542196
target language 0.00144946
source words 0.001392712
second language 0.001389464
source language 0.001377092
component words 0.001362368
descriptor language 0.001358646
probabilistic model 0.001354974
few words 0.0013546130000000002
ambiguous words 0.001351023
natural language 0.001346597
basic model 0.001336379
language ones 0.001328705
general model 0.0013236349999999999
complex words 0.001320576
language resources 0.00131518
object language 0.0013042800000000001
ranking model 0.0012512649999999999
prioritisation model 0.0012508049999999998
probability distribution 0.001195821
words 0.00110391
general translation 0.001092024
language 0.00108829
probability threshold 0.001071441
tag probability 0.001065077
right translation 0.0010619700000000002
automatic translation 0.00104012
dependency information 0.001030063
true translation 0.0010297560000000002
model 0.00102328
translation fringe 0.001007303
translation fragment 0.001002915
translation package 9.973310000000002E-4
probability distributions 9.650419999999999E-4
generation algorithm 9.496050000000001E-4
corpus evidence 9.32516E-4
frequency distribution 9.20874E-4
such collocations 9.10553E-4
correct collocations 9.0993E-4
above algorithm 8.86916E-4
glossing system 8.83709E-4
grammatical information 8.806440000000001E-4
large dictionary 8.794689999999999E-4
tiling algorithm 8.72107E-4
sorting algorithm 8.54533E-4
other criteria 8.49205E-4
enough information 8.47541E-4
information goods 8.45928E-4
production system 8.43355E-4
sid system 8.43355E-4
information gathering 8.42986E-4
other cases 8.17467E-4
input sentence 8.03654E-4
preliminary evaluation 7.933440000000001E-4
japanese dictionary 7.93166E-4
other correctness 7.917639999999999E-4
translation 7.91669E-4
bilingual corpora 7.59336E-4
frequency priority 7.47051E-4
lexical resources 7.41146E-4
bilingual equivalences 7.39714E-4
lexical material 7.39515E-4
probability 7.37925E-4
source sentence 7.36871E-4
particle collocation 7.32645E-4
collocation basis 7.30276E-4
large numbers 7.28356E-4
sentence length 7.25334E-4
particular dependency 7.20663E-4
discontinuous collocation 7.19901E-4
corpus 7.19132E-4
many types 7.12562E-4
case affixes 7.1144E-4
syntactic dependency 7.09088E-4
compactness models 7.05328E-4
many cases 7.04059E-4
ranking function 7.03192E-4
continuous collocation 6.979299999999999E-4
such cases 6.97132E-4
text fragment 6.95512E-4
typical frequency 6.95057E-4
consistent set 6.904050000000001E-4
bilingual lexicons 6.88938E-4
key descriptor 6.88387E-4
bigram tagger 6.84037E-4
recall figure 6.79395E-4
precision figure 6.7932E-4
correct ranslation 6.78621E-4
total number 6.77817E-4
first segment 6.7508E-4
correct representation 6.73901E-4
many researchers 6.73585E-4
correct matches 6.7239E-4
linguistic analysis 6.72261E-4
search radius 6.689E-4
