paraphrase sentence 0.0031398899999999998
paraphrase pairs 0.002739585
paraphrase extraction 0.0024846639999999997
extraction paraphrase 0.0024846639999999997
phrase sentence 0.0024303299999999996
candidate paraphrase 0.00241015
paraphrase candidate 0.00241015
same word 0.00240078
paraphrase classifier 0.002390269
paraphrase pair 0.0023869779999999997
paraphrase rules 0.002358757
paraphrase knowledge 0.0023436309999999997
further paraphrase 0.002340124
paraphrase instances 0.00233701
paraphrase checking 0.0023315439999999996
paraphrase acquisition 0.002303691
phrasal paraphrase 0.0022983409999999998
trivial paraphrase 0.0022715789999999997
paraphrase judgment 0.002266377
paraphrase candidates 0.002263353
paraphrase phenomena 0.002258812
valid paraphrase 0.0022565719999999997
rank paraphrase 0.002251305
phrase pairs 0.002030025
paraphrase 0.00201354
different word 0.002003736
phrase translation 0.0019352739999999998
word pairs 0.001924155
same information 0.0018796770000000002
sentence pairs 0.001852395
many paraphrases 0.0018014469999999999
web sentence 0.001781342
parallel sentence 0.001768588
phrase con 0.001734244
paraphrases figure 0.0017231059999999999
same evaluation 0.0017173230000000002
candidate phrase 0.0017005899999999999
same source 0.0016872290000000002
phrase pair 0.001677418
phrase table 0.001676017
same con 0.0016329340000000002
other words 0.001604696
noun phrase 0.001601795
incorrect paraphrases 0.001594901
same research 0.0015940330000000001
equivalent phrase 0.0015892139999999998
similarity features 0.001587935
phrasal paraphrases 0.001580021
definition sentence 0.001571393
trivial paraphrases 0.001553259
same way 0.001553005
same texts 0.0015515580000000002
first sentence 0.0015499119999999999
date phrase 0.001543779
few paraphrases 0.001543159
identical word 0.001541969
didate phrase 0.001541713
phrase segment 0.001541713
smt method 0.0015365740000000002
same concept 0.001511727
sentence pair 0.001499788
different methods 0.0014795070000000001
same linux 0.0014767650000000001
same topic 0.001471422
lexical similarity 0.001455333
web corpus 0.001443874
same cuisine 0.0014432960000000002
same pronunciation 0.0014411580000000001
parallel corpus 0.0014311200000000001
parallel sentences 0.0014232720000000002
automatic method 0.001421656
sentence acquisition 0.001416501
tion sentence 0.0013898769999999999
language model 0.0013870710000000001
sentence candidates 0.001376163
usingweb sentence 0.001370643
snippet sentence 0.0013636999999999998
supervised method 0.0013554370000000001
monolingual corpus 0.00132231
other methods 0.0013151629999999998
related words 0.001305945
phrase 0.00130398
unsupervised method 0.001301348
paraphrases 0.00129522
last words 0.00128643
method our 0.001280777
mrt method 0.0012695340000000001
corresponding words 0.0012687150000000001
proposed method 0.001264127
method murata 0.0012573060000000001
stable method 0.0012573060000000001
definition sentences 0.001226077
feature set 0.001206536
tent words 0.001203084
source text 0.001202563
feature values 0.001196338
similarity approach 0.001196052
smt methods 0.001192275
monolingual alignment 0.001189027
candidate sentences 0.001177644
