paraphrase sentences 0.002800054
phrasal paraphrase 0.0027389610000000003
paraphrase table 0.0026109210000000004
paraphrase patterns 0.00257983
paraphrase extraction 0.0025167440000000004
level paraphrase 0.00243419
paraphrase generation 0.0024091250000000002
optimal paraphrase 0.00239324
paraphrase likelihood 0.002366163
paraphrase tables 0.002351412
right paraphrase 0.002333267
paraphrase resource 0.002330726
acceptable paraphrase 0.002309058
special paraphrase 0.002307906
paraphrase options 0.002307307
recast paraphrase 0.002306254
paraphrase gen 0.0023037770000000003
paraphrase identification 0.002302536
paraphrase gener 0.002301378
phrasal paraphrases 0.002257111
same translation 0.002199483
work paraphrases 0.002162677
word pairs 0.00212356
test sentence 0.002104482
phrase pairs 0.002084
word alignment 0.002068706
paraphrase 0.00205956
translation model 0.002048767
parallel sentence 0.002036032
sentence pairs 0.00201608
source phrase 0.00200183
ing paraphrases 0.001978231
phrase table 0.001941451
source sentence 0.00193391
complex paraphrases 0.001863296
tract paraphrases 0.001848454
context words 0.001847754
phrase extraction 0.001847274
bilingual phrase 0.00183273
acceptable paraphrases 0.0018272079999999999
text sentence 0.001825635
identical word 0.001765613
phrase level 0.00176472
word definitions 0.001762793
phrase substitution 0.001760785
correct phrase 0.001745142
phrase generation 0.001739655
target phrase 0.0017360890000000001
machine translation 0.001735625
possible phrase 0.001731285
input phrase 0.001726475
word pair 0.001724872
word weights 0.001720694
many words 0.001701307
same method 0.00169424
uncommon word 0.001691377
phrase tables 0.001681942
translation sets 0.001681078
automatical word 0.001672704
phrase sub 0.001670302
test data 0.001669125
similar words 0.001665646
phrase substitutes 0.001665023
parallel corpus 0.001653128
phrase substitute 0.001637563
paraphrased sentence 0.0016362669999999998
chinese translation 0.001633041
phrase substi 0.0016326630000000001
sentence fragments 0.0016090879999999998
parallel data 0.001600675
equivalent translation 0.0015965699999999998
paraphrases 0.00157771
translation informa 0.0015773109999999999
translation probabil 0.0015685249999999999
language model 0.001553136
monolingual corpus 0.0015421710000000002
identical words 0.0015368130000000002
different test 0.001533827
large corpus 0.001524231
test sentences 0.0015228059999999998
same source 0.001495883
different news 0.001464257
parallel sentences 0.001454356
news sentences 0.0014532360000000001
phrase 0.00139009
smt model 0.001368309
context similarity 0.001357701
training data 0.001344479
sentence 0.00132217
monolingual parallel 0.001316767
translation 0.00131534
source phrases 0.001289664
test set 0.00127712
comparable corpus 0.001262089
parallel corpora 0.001242549
monolingual smt 0.0012377870000000002
smt system 0.0012337580000000002
same meaning 0.001222678
second language 0.0012089709999999999
words 0.00120085
